Overview
| title | abstract |
|---|---|
| Synthetic Test Collections for Retrieval Evaluation | Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging, and acquiring relevance judgments, which indicate the appropriateness of retrieved documents to a query, is often costly and resource-intensive. Generating synthetic datasets using Large Language Models (LLMs) has recently gained significant attention in various applications. In IR, while previous work exploited the capabilities of LLMs to generate synthetic queries or documents to augment training data and improve the performance of ranking models, using LLMs for constructing synthetic test collections is relatively unexplored. Previous studies demonstrate that LLMs have the potential to generate synthetic relevance judgments for use in the evaluation of IR systems. In this paper, we comprehensively investigate whether it is possible to use LLMs to construct fully synthetic test collections by generating not only synthetic judgments but also synthetic queries. In particular, we analyse whether it is possible to construct reliable synthetic test collections and the potential risks of bias such test collections may exhibit towards LLM-based models. Our experiments indicate that using LLMs it is possible to construct synthetic test collections that can reliably be used for retrieval evaluation. |
| Synthetic Test Collections for Retrieval Evaluation | Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging, and acquiring relevance judgments, which indicate the appropriateness of retrieved documents to a query, is often costly and resource-intensive. Generating synthetic datasets using Large Language Models (LLMs) has recently gained significant attention in various applications. In IR, while previous work exploited the capabilities of LLMs to generate synthetic queries or documents to augment training data and improve the performance of ranking models, using LLMs for constructing synthetic test collections is relatively unexplored. Previous studies demonstrate that LLMs have the potential to generate synthetic relevance judgments for use in the evaluation of IR systems. In this paper, we comprehensively investigate whether it is possible to use LLMs to construct fully synthetic test collections by generating not only synthetic judgments but also synthetic queries. In particular, we analyse whether it is possible to construct reliable synthetic test collections and the potential risks of bias such test collections may exhibit towards LLM-based models. Our experiments indicate that using LLMs it is possible to construct synthetic test collections that can reliably be used for retrieval evaluation. |
| ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs | Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data, aiming to enhance the debiasing of LLMs. We propose two strategies: Targeted Prompting, which provides effective debiasing for known biases but necessitates prior specification of bias in question; and General Prompting, which, while slightly less effective, offers debiasing across various categories. We leverage resource-efficient LLM debiasing using adapter tuning and compare the effectiveness of our synthetic data to existing debiasing datasets. Our results reveal that: (1) ChatGPT can efficiently produce high-quality training data for debiasing other LLMs; (2) data produced via our approach surpasses existing datasets in debiasing performance while also preserving internal knowledge of a pre-trained LLM; and (3) synthetic data exhibits generalizability across categories, effectively mitigating various biases, including intersectional ones. These findings underscore the potential of synthetic data in advancing the fairness of LLMs with minimal retraining cost. |
| Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations | The collection and curation of high-quality training data is crucial for developing text classification models with superior performance, but it is often associated with significant costs and time investment. Researchers have recently explored using large language models (LLMs) to generate synthetic datasets as an alternative approach. However, the effectiveness of the LLM-generated synthetic data in supporting model training is inconsistent across different classification tasks. To better understand factors that moderate the effectiveness of the LLM-generated synthetic data, in this study, we look into how the performance of models trained on these synthetic data may vary with the subjectivity of classification. Our results indicate that subjectivity, at both the task level and instance level, is negatively associated with the performance of the model trained on synthetic data. We conclude by discussing the implications of our work on the potential and limitations of leveraging LLM for synthetic data generation. |
| Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data | As large language models (LLMs) demonstrate unparalleled performance and generalization ability, LLMs are widely used and integrated into various applications. When it comes to sensitive domains, as commonly described in federated learning scenarios, directly using external LLMs on private data is strictly prohibited by stringent data security and privacy regulations. For local clients, the utilization of LLMs to improve the domain-specific small language models (SLMs), characterized by limited computational resources and domain-specific data, has attracted considerable research attention. By observing that LLMs can empower domain-specific SLMs, existing methods predominantly concentrate on leveraging the public data or LLMs to generate more data to transfer knowledge from LLMs to SLMs. However, due to the discrepancies between LLMs' generated data and clients' domain-specific data, these methods cannot yield substantial improvements in the domain-specific tasks. In this paper, we introduce a Federated Domain-specific Knowledge Transfer (FDKT) framework, which enables domain-specific knowledge transfer from LLMs to SLMs while preserving clients' data privacy. The core insight is to leverage LLMs to augment data based on domain-specific few-shot demonstrations, which are synthesized from private domain data using differential privacy. Such synthetic samples share similar data distribution with clients' private data and allow the server LLM to generate particular knowledge to improve clients' SLMs. The extensive experimental results demonstrate that the proposed FDKT framework consistently and greatly improves SLMs' task performance by around 5\% with a privacy budget of less than 10, compared to local training on private data. |
| Differentially Private Synthetic Data via Foundation Model APIs 2: Text | Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to privacy concerns. Generating synthetic replicas of private text data with a formal privacy guarantee, i.e., differential privacy (DP), offers a promising and scalable solution. However, existing methods necessitate DP finetuning of large language models (LLMs) on private data to generate DP synthetic data. This approach is not viable for proprietary LLMs (e.g., GPT-3.5) and also demands considerable computational resources for open-source LLMs. Lin et al. (2024) recently introduced the Private Evolution (PE) algorithm to generate DP synthetic images with only API access to diffusion models. In this work, we propose an augmented PE algorithm, named Aug-PE, that applies to the complex setting of text. We use API access to an LLM and generate DP synthetic text without any model training. We conduct comprehensive experiments on three benchmark datasets. Our results demonstrate that Aug-PE produces DP synthetic text that yields competitive utility with the SOTA DP finetuning baselines. This underscores the feasibility of relying solely on API access of LLMs to produce high-quality DP synthetic texts, thereby facilitating more accessible routes to privacy-preserving LLM applications. Our code and data are available at https://github.com/AI-secure/aug-pe. |
| Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal | Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications. When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent. To address this challenge, we propose a framework called Self-Synthesized Rehearsal (SSR) that uses the LLM to generate synthetic instances for rehearsal. Concretely, we first employ the base LLM for in-context learning to generate synthetic instances. Subsequently, we utilize the latest LLM to refine the instance outputs based on the synthetic inputs, preserving its acquired ability. Finally, we select diverse high-quality synthetic instances for rehearsal in future stages. Experimental results demonstrate that SSR achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient. Besides, SSR effectively preserves the generalization capabilities of LLMs in general domains. |
| Exploring LLMs as a Source of Targeted Synthetic Textual Data to Minimize High Confidence Misclassifications | Natural Language Processing (NLP) models optimized for predictive performance often make high confidence errors and suffer from vulnerability to adversarial and out-of-distribution data. Existing work has mainly focused on mitigation of such errors using either humans or an automated approach. In this study, we explore the usage of large language models (LLMs) for data augmentation as a potential solution to the issue of NLP models making wrong predictions with high confidence during classification tasks. We compare the effectiveness of synthetic data generated by LLMs with that of human data obtained via the same procedure. For mitigation, humans or LLMs provide natural language characterizations of high confidence misclassifications to generate synthetic data, which are then used to extend the training set. We conduct an extensive evaluation of our approach on three classification tasks and demonstrate its effectiveness in reducing the number of high confidence misclassifications present in the model, all while maintaining the same level of accuracy. Moreover, we find that the cost gap between humans and LLMs surpasses an order of magnitude, as LLMs attain human-like performance while being more scalable. |
| S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models | The rapid development of Large Language Models (LLMs) has led to great strides in model capabilities like long-context understanding and reasoning. However, as LLMs are able to process longer contexts, it becomes more challenging to evaluate whether they have acquired certain capabilities, since the length of text (e.g., 200K tokens) they can process far exceeds what humans can reliably assess in a reasonable duration. In this paper, we propose using complex synthetic tasks as a proxy evaluation method, and present S3Eval, a Synthetic, Scalable, Systematic evaluation suite for LLMs evaluation. The synthetic nature of S3Eval provides users full control over the dataset, allowing them to systematically probe LLM capabilities by scaling text length and varying task difficulty across diverse scenarios. The strong correlation between S3Eval and real-world benchmarks demonstrates the soundness of using S3Eval for evaluation of LLMs. S3Eval provides a flexible and infinite long-context data generation method. We have generated a comprehensive dataset called S3Eval-Standard, and experimental results have shown that it poses significant challenges for all existing LLMs. |
| MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents | Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of "fact-checking" are based on verifying each piece of a model generation against potential evidence using an LLM. However, this process can be very computationally expensive, requiring many calls to LLMs to check a single response. In this work, we show how to build small models that have GPT-4-level performance but for 400x lower cost. We do this by constructing synthetic training data with GPT-4, which involves creating realistic yet challenging instances of factual errors via a structured generation procedure. Training on this data teaches models to check each fact in the claim and recognize synthesis of information across sentences. For evaluation, we unify pre-existing datasets into a benchmark LLM-AggreFact, collected from recent work on fact-checking and grounding LLM generations. Our best system MiniCheck-FT5 (770M parameters) outperforms all systems of comparable size and reaches GPT-4 accuracy. We release LLM-AggreFact, code for data synthesis, and models. |
| Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks | Large language models (LLMs) are remarkable data annotators. They can be used to generate high-fidelity supervised training data, as well as survey and experimental data. With the widespread adoption of LLMs, human gold--standard annotations are key to understanding the capabilities of LLMs and the validity of their results. However, crowdsourcing, an important, inexpensive way to obtain human annotations, may itself be impacted by LLMs, as crowd workers have financial incentives to use LLMs to increase their productivity and income. To investigate this concern, we conducted a case study on the prevalence of LLM usage by crowd workers. We reran an abstract summarization task from the literature on Amazon Mechanical Turk and, through a combination of keystroke detection and synthetic text classification, estimate that 33-46% of crowd workers used LLMs when completing the task. Although generalization to other, less LLM-friendly tasks is unclear, our results call for platforms, researchers, and crowd workers to find new ways to ensure that human data remain human, perhaps using the methodology proposed here as a stepping stone. Code/data: https://github.com/epfl-dlab/GPTurk |
| Synthetic Test Collections for Retrieval Evaluation | Test collections play a vital role in evaluation of information retrieval (IR) systems. Obtaining a diverse set of user queries for test collection construction can be challenging, and acquiring relevance judgments, which indicate the appropriateness of retrieved documents to a query, is often costly and resource-intensive. Generating synthetic datasets using Large Language Models (LLMs) has recently gained significant attention in various applications. In IR, while previous work exploited the capabilities of LLMs to generate synthetic queries or documents to augment training data and improve the performance of ranking models, using LLMs for constructing synthetic test collections is relatively unexplored. Previous studies demonstrate that LLMs have the potential to generate synthetic relevance judgments for use in the evaluation of IR systems. In this paper, we comprehensively investigate whether it is possible to use LLMs to construct fully synthetic test collections by generating not only synthetic judgments but also synthetic queries. In particular, we analyse whether it is possible to construct reliable synthetic test collections and the potential risks of bias such test collections may exhibit towards LLM-based models. Our experiments indicate that using LLMs it is possible to construct synthetic test collections that can reliably be used for retrieval evaluation. |
| ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs | Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data, aiming to enhance the debiasing of LLMs. We propose two strategies: Targeted Prompting, which provides effective debiasing for known biases but necessitates prior specification of bias in question; and General Prompting, which, while slightly less effective, offers debiasing across various categories. We leverage resource-efficient LLM debiasing using adapter tuning and compare the effectiveness of our synthetic data to existing debiasing datasets. Our results reveal that: (1) ChatGPT can efficiently produce high-quality training data for debiasing other LLMs; (2) data produced via our approach surpasses existing datasets in debiasing performance while also preserving internal knowledge of a pre-trained LLM; and (3) synthetic data exhibits generalizability across categories, effectively mitigating various biases, including intersectional ones. These findings underscore the potential of synthetic data in advancing the fairness of LLMs with minimal retraining cost. |
| Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations | The collection and curation of high-quality training data is crucial for developing text classification models with superior performance, but it is often associated with significant costs and time investment. Researchers have recently explored using large language models (LLMs) to generate synthetic datasets as an alternative approach. However, the effectiveness of the LLM-generated synthetic data in supporting model training is inconsistent across different classification tasks. To better understand factors that moderate the effectiveness of the LLM-generated synthetic data, in this study, we look into how the performance of models trained on these synthetic data may vary with the subjectivity of classification. Our results indicate that subjectivity, at both the task level and instance level, is negatively associated with the performance of the model trained on synthetic data. We conclude by discussing the implications of our work on the potential and limitations of leveraging LLM for synthetic data generation. |
| Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data | As large language models (LLMs) demonstrate unparalleled performance and generalization ability, LLMs are widely used and integrated into various applications. When it comes to sensitive domains, as commonly described in federated learning scenarios, directly using external LLMs on private data is strictly prohibited by stringent data security and privacy regulations. For local clients, the utilization of LLMs to improve the domain-specific small language models (SLMs), characterized by limited computational resources and domain-specific data, has attracted considerable research attention. By observing that LLMs can empower domain-specific SLMs, existing methods predominantly concentrate on leveraging the public data or LLMs to generate more data to transfer knowledge from LLMs to SLMs. However, due to the discrepancies between LLMs' generated data and clients' domain-specific data, these methods cannot yield substantial improvements in the domain-specific tasks. In this paper, we introduce a Federated Domain-specific Knowledge Transfer (FDKT) framework, which enables domain-specific knowledge transfer from LLMs to SLMs while preserving clients' data privacy. The core insight is to leverage LLMs to augment data based on domain-specific few-shot demonstrations, which are synthesized from private domain data using differential privacy. Such synthetic samples share similar data distribution with clients' private data and allow the server LLM to generate particular knowledge to improve clients' SLMs. The extensive experimental results demonstrate that the proposed FDKT framework consistently and greatly improves SLMs' task performance by around 5\% with a privacy budget of less than 10, compared to local training on private data. |
| Differentially Private Synthetic Data via Foundation Model APIs 2: Text | Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to privacy concerns. Generating synthetic replicas of private text data with a formal privacy guarantee, i.e., differential privacy (DP), offers a promising and scalable solution. However, existing methods necessitate DP finetuning of large language models (LLMs) on private data to generate DP synthetic data. This approach is not viable for proprietary LLMs (e.g., GPT-3.5) and also demands considerable computational resources for open-source LLMs. Lin et al. (2024) recently introduced the Private Evolution (PE) algorithm to generate DP synthetic images with only API access to diffusion models. In this work, we propose an augmented PE algorithm, named Aug-PE, that applies to the complex setting of text. We use API access to an LLM and generate DP synthetic text without any model training. We conduct comprehensive experiments on three benchmark datasets. Our results demonstrate that Aug-PE produces DP synthetic text that yields competitive utility with the SOTA DP finetuning baselines. This underscores the feasibility of relying solely on API access of LLMs to produce high-quality DP synthetic texts, thereby facilitating more accessible routes to privacy-preserving LLM applications. Our code and data are available at https://github.com/AI-secure/aug-pe. |
| Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal | Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications. When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent. To address this challenge, we propose a framework called Self-Synthesized Rehearsal (SSR) that uses the LLM to generate synthetic instances for rehearsal. Concretely, we first employ the base LLM for in-context learning to generate synthetic instances. Subsequently, we utilize the latest LLM to refine the instance outputs based on the synthetic inputs, preserving its acquired ability. Finally, we select diverse high-quality synthetic instances for rehearsal in future stages. Experimental results demonstrate that SSR achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient. Besides, SSR effectively preserves the generalization capabilities of LLMs in general domains. |
| Exploring LLMs as a Source of Targeted Synthetic Textual Data to Minimize High Confidence Misclassifications | Natural Language Processing (NLP) models optimized for predictive performance often make high confidence errors and suffer from vulnerability to adversarial and out-of-distribution data. Existing work has mainly focused on mitigation of such errors using either humans or an automated approach. In this study, we explore the usage of large language models (LLMs) for data augmentation as a potential solution to the issue of NLP models making wrong predictions with high confidence during classification tasks. We compare the effectiveness of synthetic data generated by LLMs with that of human data obtained via the same procedure. For mitigation, humans or LLMs provide natural language characterizations of high confidence misclassifications to generate synthetic data, which are then used to extend the training set. We conduct an extensive evaluation of our approach on three classification tasks and demonstrate its effectiveness in reducing the number of high confidence misclassifications present in the model, all while maintaining the same level of accuracy. Moreover, we find that the cost gap between humans and LLMs surpasses an order of magnitude, as LLMs attain human-like performance while being more scalable. |
| S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models | The rapid development of Large Language Models (LLMs) has led to great strides in model capabilities like long-context understanding and reasoning. However, as LLMs are able to process longer contexts, it becomes more challenging to evaluate whether they have acquired certain capabilities, since the length of text (e.g., 200K tokens) they can process far exceeds what humans can reliably assess in a reasonable duration. In this paper, we propose using complex synthetic tasks as a proxy evaluation method, and present S3Eval, a Synthetic, Scalable, Systematic evaluation suite for LLMs evaluation. The synthetic nature of S3Eval provides users full control over the dataset, allowing them to systematically probe LLM capabilities by scaling text length and varying task difficulty across diverse scenarios. The strong correlation between S3Eval and real-world benchmarks demonstrates the soundness of using S3Eval for evaluation of LLMs. S3Eval provides a flexible and infinite long-context data generation method. We have generated a comprehensive dataset called S3Eval-Standard, and experimental results have shown that it poses significant challenges for all existing LLMs. |
| MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents | Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of "fact-checking" are based on verifying each piece of a model generation against potential evidence using an LLM. However, this process can be very computationally expensive, requiring many calls to LLMs to check a single response. In this work, we show how to build small models that have GPT-4-level performance but for 400x lower cost. We do this by constructing synthetic training data with GPT-4, which involves creating realistic yet challenging instances of factual errors via a structured generation procedure. Training on this data teaches models to check each fact in the claim and recognize synthesis of information across sentences. For evaluation, we unify pre-existing datasets into a benchmark LLM-AggreFact, collected from recent work on fact-checking and grounding LLM generations. Our best system MiniCheck-FT5 (770M parameters) outperforms all systems of comparable size and reaches GPT-4 accuracy. We release LLM-AggreFact, code for data synthesis, and models. |
| Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks | Large language models (LLMs) are remarkable data annotators. They can be used to generate high-fidelity supervised training data, as well as survey and experimental data. With the widespread adoption of LLMs, human gold--standard annotations are key to understanding the capabilities of LLMs and the validity of their results. However, crowdsourcing, an important, inexpensive way to obtain human annotations, may itself be impacted by LLMs, as crowd workers have financial incentives to use LLMs to increase their productivity and income. To investigate this concern, we conducted a case study on the prevalence of LLM usage by crowd workers. We reran an abstract summarization task from the literature on Amazon Mechanical Turk and, through a combination of keystroke detection and synthetic text classification, estimate that 33-46% of crowd workers used LLMs when completing the task. Although generalization to other, less LLM-friendly tasks is unclear, our results call for platforms, researchers, and crowd workers to find new ways to ensure that human data remain human, perhaps using the methodology proposed here as a stepping stone. Code/data: https://github.com/epfl-dlab/GPTurk |
| title | abstract |
|---|---|
| Humans or LLMs as the Judge? A Study on Judgement Biases | Adopting human and large language models (LLM) as judges (\textit{a.k.a} human- and LLM-as-a-judge) for evaluating the performance of LLMs has recently gained attention. Nonetheless, this approach concurrently introduces potential biases from human and LLM judges, questioning the reliability of the evaluation results. In this paper, we propose a novel framework that is free from referencing groundtruth annotations for investigating Fallacy Oversight Bias, Authority Bias and Beauty Bias on LLM and human judges. We curate a dataset referring to the revised Bloom's Taxonomy and conduct thousands of human and LLM evaluations. Results show that human and LLM judges are vulnerable to perturbations to various degrees, and that even the cutting-edge judges possess considerable biases. We further exploit their weakness and conduct attacks on LLM judges. We hope that our work can notify the community of the vulnerability of human- and LLM-as-a-judge against perturbations, as well as the urgency of developing robust evaluation systems. |
| Can LLM be a Personalized Judge? | Ensuring that large language models (LLMs) reflect diverse user values and preferences is crucial as their user bases expand globally. It is therefore encouraging to see the growing interest in LLM personalization within the research community. However, current works often rely on the LLM-as-a-Judge approach for evaluation without thoroughly examining its validity. In this paper, we investigate the reliability of LLM-as-a-Personalized-Judge, asking LLMs to judge user preferences based on personas. Our findings suggest that directly applying LLM-as-a-Personalized-Judge is less reliable than previously assumed, showing low and inconsistent agreement with human ground truth. The personas typically used are often overly simplistic, resulting in low predictive power. To address these issues, we introduce verbal uncertainty estimation into the LLM-as-a-Personalized-Judge pipeline, allowing the model to express low confidence on uncertain judgments. This adjustment leads to much higher agreement (above 80%) on high-certainty samples for binary tasks. Through human evaluation, we find that the LLM-as-a-Personalized-Judge achieves comparable performance to third-party humans evaluation and even surpasses human performance on high-certainty samples. Our work indicates that certainty-enhanced LLM-as-a-Personalized-Judge offers a promising direction for developing more reliable and scalable methods for evaluating LLM personalization. |
| On the Limitations of Fine-tuned Judge Models for LLM Evaluation | Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs. Many studies have employed proprietary close-source models, especially GPT-4, as the evaluator. Alternatively, other works have fine-tuned judge models based on open-source LLMs as the evaluator. While the fine-tuned judge models are claimed to achieve comparable evaluation capability with GPT-4, in this study, we conduct an empirical study of judge models. Our findings indicate that although the fine-tuned judge models achieve high performance on in-domain test sets, even surpassing GPT-4, they underperform GPT-4 across several dimensions, including generalizability, fairness, aspect-specific evaluation, and scalability. We also reveal that the fine-tuned judge model inherently operates as a task-specific classifier, consequently imposing the limitations. Finally, we propose an effective indicator to measure the reliability of fine-tuned judges, with the aim of maximizing their utility in LLM evaluation. |
| JudgeLM: Fine-tuned Large Language Models are Scalable Judges | Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B, to 33B parameters, and conduct a systematic analysis of its capabilities and behaviors. We then analyze the key biases in fine-tuning LLM as a judge and consider them as position bias, knowledge bias, and format bias. To address these issues, JudgeLM introduces a bag of techniques including swap augmentation, reference support, and reference drop, which clearly enhance the judge's performance. JudgeLM obtains the state-of-the-art judge performance on both the existing PandaLM benchmark and our proposed new benchmark. Our JudgeLM is efficient and the JudgeLM-7B only needs 3 minutes to judge 5K samples with 8 A100 GPUs. JudgeLM obtains high agreement with the teacher judge, achieving an agreement exceeding 90% that even surpasses human-to-human agreement. JudgeLM also demonstrates extended capabilities in being judges of the single answer, multimodal models, multiple answers, and multi-turn chat. |
| Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment | Large Language Models (LLMs) are powerful zero-shot assessors and are increasingly used in real-world situations such as for written exams or benchmarking systems. Despite this, no existing work has analyzed the vulnerability of judge-LLMs against adversaries attempting to manipulate outputs. This work presents the first study on the adversarial robustness of assessment LLMs, where we search for short universal phrases that when appended to texts can deceive LLMs to provide high assessment scores. Experiments on SummEval and TopicalChat demonstrate that both LLM-scoring and pairwise LLM-comparative assessment are vulnerable to simple concatenation attacks, where in particular LLM-scoring is very susceptible and can yield maximum assessment scores irrespective of the input text quality. Interestingly, such attacks are transferable and phrases learned on smaller open-source LLMs can be applied to larger closed-source models, such as GPT3.5. This highlights the pervasive nature of the adversarial vulnerabilities across different judge-LLM sizes, families and methods. Our findings raise significant concerns on the reliability of LLMs-as-a-judge methods, and underscore the importance of addressing vulnerabilities in LLM assessment methods before deployment in high-stakes real-world scenarios. |
| Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models | As Large Language Models (LLMs) have become more advanced, they have outpaced our abilities to accurately evaluate their quality. Not only is finding data to adequately probe particular model properties difficult, but evaluating the correctness of a model's freeform generation alone is a challenge. To address this, many evaluations now rely on using LLMs themselves as judges to score the quality of outputs from other LLMs. Evaluations most commonly use a single large model like GPT4. While this method has grown in popularity, it is costly, has been shown to introduce intramodel bias, and in this work, we find that very large models are often unnecessary. We propose instead to evaluate models using a Panel of LLm evaluators (PoLL). Across three distinct judge settings and spanning six different datasets, we find that using a PoLL composed of a larger number of smaller models outperforms a single large judge, exhibits less intra-model bias due to its composition of disjoint model families, and does so while being over seven times less expensive. |
| Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models | Recent researches indicate that Pre-trained Large Language Models (LLMs) possess cognitive constructs similar to those observed in humans, prompting researchers to investigate the cognitive aspects of LLMs. This paper focuses on explicit and implicit social bias, a distinctive two-level cognitive construct in psychology. It posits that individuals' explicit social bias, which is their conscious expression of bias in the statements, may differ from their implicit social bias, which represents their unconscious bias. We propose a two-stage approach and discover a parallel phenomenon in LLMs known as "re-judge inconsistency" in social bias. In the initial stage, the LLM is tasked with automatically completing statements, potentially incorporating implicit social bias. However, in the subsequent stage, the same LLM re-judges the biased statement generated by itself but contradicts it. We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias. Experimental investigations on ChatGPT and GPT-4 concerning common gender biases examined in psychology corroborate the highly stable nature of the re-judge inconsistency. This finding may suggest that diverse cognitive constructs emerge as LLMs' capabilities strengthen. Consequently, leveraging psychological theories can provide enhanced insights into the underlying mechanisms governing the expressions of explicit and implicit constructs in LLMs. |
| Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena | Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-bench, a multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our results reveal that strong LLM judges like GPT-4 can match both controlled and crowdsourced human preferences well, achieving over 80% agreement, the same level of agreement between humans. Hence, LLM-as-a-judge is a scalable and explainable way to approximate human preferences, which are otherwise very expensive to obtain. Additionally, we show our benchmark and traditional benchmarks complement each other by evaluating several variants of LLaMA and Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with human preferences are publicly available at https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge. |
| Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs | The advent of Large Language Models (LLMs) has significantly transformed the AI landscape, enhancing machine learning and AI capabilities. Factuality issue is a critical concern for LLMs, as they may generate factually incorrect responses. In this paper, we propose GraphEval to evaluate an LLM's performance using a substantially large test dataset. Specifically, the test dataset is retrieved from a large knowledge graph with more than 10 million facts without expensive human efforts. Unlike conventional methods that evaluate LLMs based on generated responses, GraphEval streamlines the evaluation process by creating a judge model to estimate the correctness of the answers given by the LLM. Our experiments demonstrate that the judge model's factuality assessment aligns closely with the correctness of the LLM's generated outputs, while also substantially reducing evaluation costs. Besides, our findings offer valuable insights into LLM performance across different metrics and highlight the potential for future improvements in ensuring the factual integrity of LLM outputs. The code is publicly available at https://github.com/xz-liu/GraphEval. |
| Can Many-Shot In-Context Learning Help Long-Context LLM Judges? See More, Judge Better! | Leveraging Large Language Models (LLMs) as judges for evaluating the performance of LLMs has recently garnered attention. Nonetheless, this type of approach concurrently introduces potential biases from LLMs, raising concerns about the reliability of the evaluation results. To mitigate this issue, we propose and study two versions of many-shot in-context prompts, Reinforced and Unsupervised ICL, for helping GPT-4o-as-a-Judge in single answer grading. Based on the designed prompts, we investigate the impact of scaling the number of in-context examples on the agreement and quality of the evaluation. Furthermore, we first reveal the symbol bias in GPT-4o-as-a-Judge for pairwise comparison and then propose a simple yet effective approach to mitigate it. Experimental results show that advanced long-context LLMs, such as GPT-4o, perform better in the many-shot regime than in the zero-shot regime. Meanwhile, the experimental results further verify the effectiveness of the symbol bias mitigation approach. |
| title | abstract |
|---|---|
| MEGAnno+: A Human-LLM Collaborative Annotation System | Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to incorrect annotations. Therefore, we advocate a collaborative approach where humans and LLMs work together to produce reliable and high-quality labels. We present MEGAnno+, a human-LLM collaborative annotation system that offers effective LLM agent and annotation management, convenient and robust LLM annotation, and exploratory verification of LLM labels by humans. |
| A Comparative Study on Annotation Quality of Crowdsourcing and LLM via Label Aggregation | Whether Large Language Models (LLMs) can outperform crowdsourcing on the data annotation task is attracting interest recently. Some works verified this issue with the average performance of individual crowd workers and LLM workers on some specific NLP tasks by collecting new datasets. However, on the one hand, existing datasets for the studies of annotation quality in crowdsourcing are not yet utilized in such evaluations, which potentially provide reliable evaluations from a different viewpoint. On the other hand, the quality of these aggregated labels is crucial because, when utilizing crowdsourcing, the estimated labels aggregated from multiple crowd labels to the same instances are the eventually collected labels. Therefore, in this paper, we first investigate which existing crowdsourcing datasets can be used for a comparative study and create a benchmark. We then compare the quality between individual crowd labels and LLM labels and make the evaluations on the aggregated labels. In addition, we propose a Crowd-LLM hybrid label aggregation method and verify the performance. We find that adding LLM labels from good LLMs to existing crowdsourcing datasets can enhance the quality of the aggregated labels of the datasets, which is also higher than the quality of LLM labels themselves. |
| Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning | Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the data with the student model being finetuned. This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM's reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing instruction-tuning data. This teacher-student collaboration produces high-quality and student-compatible instruction-response pairs, resulting in sample-efficient instruction tuning and LLMs of superior performance. Selective Reflection-Tuning is a data augmentation and synthesis that generally improves LLM finetuning and self-improvement without collecting brand-new data. We apply our method to Alpaca and WizardLM data and achieve much stronger and top-tier 7B and 13B LLMs. |
| Label-free Node Classification on Graphs with Large Language Models (LLMS) | In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to ensure promising performance. In contrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiency on text-attributed graphs. Yet, they face challenges in efficiently processing structural data and suffer from high inference costs. In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMs while mitigating their limitations. Specifically, LLMs are leveraged to annotate a small portion of nodes and then GNNs are trained on LLMs' annotations to make predictions for the remaining large portion of nodes. The implementation of LLM-GNN faces a unique challenge: how can we actively select nodes for LLMs to annotate and consequently enhance the GNN training? How can we leverage LLMs to obtain annotations of high quality, representativeness, and diversity, thereby enhancing GNN performance with less cost? To tackle this challenge, we develop an annotation quality heuristic and leverage the confidence scores derived from LLMs to advanced node selection. Comprehensive experimental results validate the effectiveness of LLM-GNN. In particular, LLM-GNN can achieve an accuracy of 74.9% on a vast-scale dataset \products with a cost less than 1 dollar. |
| OPDAI at SemEval-2024 Task 6: Small LLMs can Accelerate Hallucination Detection with Weakly Supervised Data | This paper mainly describes a unified system for hallucination detection of LLMs, which wins the second prize in the model-agnostic track of the SemEval-2024 Task 6, and also achieves considerable results in the model-aware track. This task aims to detect hallucination with LLMs for three different text-generation tasks without labeled training data. We utilize prompt engineering and few-shot learning to verify the performance of different LLMs on the validation data. Then we select the LLMs with better performance to generate high-quality weakly supervised training data, which not only satisfies the consistency of different LLMs, but also satisfies the consistency of the optimal LLM with different sampling parameters. Furthermore, we finetune different LLMs by using the constructed training data, and finding that a relatively small LLM can achieve a competitive level of performance in hallucination detection, when compared to the large LLMs and the prompt-based approaches using GPT-4. |
| METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualities | Large-Language Models (LLMs) have shifted the paradigm of natural language data processing. However, their black-boxed and probabilistic characteristics can lead to potential risks in the quality of outputs in diverse LLM applications. Recent studies have tested Quality Attributes (QAs), such as robustness or fairness, of LLMs by generating adversarial input texts. However, existing studies have limited their coverage of QAs and tasks in LLMs and are difficult to extend. Additionally, these studies have only used one evaluation metric, Attack Success Rate (ASR), to assess the effectiveness of their approaches. We propose a MEtamorphic Testing for Analyzing LLMs (METAL) framework to address these issues by applying Metamorphic Testing (MT) techniques. This approach facilitates the systematic testing of LLM qualities by defining Metamorphic Relations (MRs), which serve as modularized evaluation metrics. The METAL framework can automatically generate hundreds of MRs from templates that cover various QAs and tasks. In addition, we introduced novel metrics that integrate the ASR method into the semantic qualities of text to assess the effectiveness of MRs accurately. Through the experiments conducted with three prominent LLMs, we have confirmed that the METAL framework effectively evaluates essential QAs on primary LLM tasks and reveals the quality risks in LLMs. Moreover, the newly proposed metrics can guide the optimal MRs for testing each task and suggest the most effective method for generating MRs. |
| Towards Training A Chinese Large Language Model for Anesthesiology | Medical large language models (LLMs) have gained popularity recently due to their significant practical utility. However, most existing research focuses on general medicine, and there is a need for in-depth study of LLMs in specific fields like anesthesiology. To fill the gap, we introduce Hypnos, a Chinese Anesthesia model built upon existing LLMs, e.g., Llama. Hypnos' contributions have three aspects: 1) The data, such as utilizing Self-Instruct, acquired from current LLMs likely includes inaccuracies. Hypnos implements a cross-filtering strategy to improve the data quality. This strategy involves using one LLM to assess the quality of the generated data from another LLM and filtering out the data with low quality. 2) Hypnos employs a general-to-specific training strategy that starts by fine-tuning LLMs using the general medicine data and subsequently improving the fine-tuned LLMs using data specifically from Anesthesiology. The general medical data supplement the medical expertise in Anesthesiology and enhance the effectiveness of Hypnos' generation. 3) We introduce a standardized benchmark for evaluating medical LLM in Anesthesiology. Our benchmark includes both publicly available instances from the Internet and privately obtained cases from the Hospital. Hypnos outperforms other medical LLMs in anesthesiology in metrics, GPT-4, and human evaluation on the benchmark dataset. |
| FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models | Large Language Models (LLMs), such as ChatGPT, LLaMA, GLM, and PaLM, have exhibited remarkable performances across various tasks in recent years. However, LLMs face two main challenges in real-world applications. One challenge is that training LLMs consumes vast computing resources, preventing LLMs from being adopted by small and medium-sized enterprises with limited computing resources. Another is that training LLM requires a large amount of high-quality data, which are often scattered among enterprises. To address these challenges, we propose FATE-LLM, an industrial-grade federated learning framework for large language models. FATE-LLM (1) facilitates federated learning for large language models (coined FedLLM); (2) promotes efficient training of FedLLM using parameter-efficient fine-tuning methods; (3) protects the intellectual property of LLMs; (4) preserves data privacy during training and inference through privacy-preserving mechanisms. We release the code of FATE-LLM at https://github.com/FederatedAI/FATE-LLM to facilitate the research of FedLLM and enable a broad range of industrial applications. |
| Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements | Making LLMs speak for different, especially minority groups of people, and generate statements supporting their diverse or even controversial perspectives is critical to creating an inclusive environment. However, existing LLMs lack sufficient controllability to the stance of their generated content, which often contains inconsistent, neutral, or biased statements. In this paper, we improve the controllability of LLMs in generating statements supporting an argument the user defined in the prompt. We find that multi-round debates between two LLMs with opposite stances generate higher-quality and more salient statements for each, which are important training data to improve the controllability of LLMs. Motivated by this, we develop a novel debate & tuning (DEBATUNE) pipeline finetuning LLMs to generate the statements obtained via debate. To examine DEBATUNE, we curate the largest dataset of debate topics so far, which covers 710 controversial topics and corresponding arguments for each topic. Evaluations by the GPT-4 judge with a novel controversy controllability metric show that LLMs' capability of generating diverse perspectives is significantly improved by DEBATUNE. Moreover, such controllability can be generalized to unseen topics, generating high-quality statements supporting controversial arguments. |
| Large Language Models and User Trust: Consequence of Self-Referential Learning Loop and the Deskilling of Healthcare Professionals | This paper explores the evolving relationship between clinician trust in LLMs, the transformation of data sources from predominantly human-generated to AI-generated content, and the subsequent impact on the precision of LLMs and clinician competence. One of the primary concerns identified is the potential feedback loop that arises as LLMs become more reliant on their outputs for learning, which may lead to a degradation in output quality and a reduction in clinician skills due to decreased engagement with fundamental diagnostic processes. While theoretical at this stage, this feedback loop poses a significant challenge as the integration of LLMs in healthcare deepens, emphasizing the need for proactive dialogue and strategic measures to ensure the safe and effective use of LLM technology. A key takeaway from our investigation is the critical role of user expertise and the necessity for a discerning approach to trusting and validating LLM outputs. The paper highlights how expert users, particularly clinicians, can leverage LLMs to enhance productivity by offloading routine tasks while maintaining a critical oversight to identify and correct potential inaccuracies in AI-generated content. This balance of trust and skepticism is vital for ensuring that LLMs augment rather than undermine the quality of patient care. Moreover, we delve into the potential risks associated with LLMs' self-referential learning loops and the deskilling of healthcare professionals. The risk of LLMs operating within an echo chamber, where AI-generated content feeds into the learning algorithms, threatens the diversity and quality of the data pool, potentially entrenching biases and reducing the efficacy of LLMs. |
| title | abstract |
|---|---|
| LLM A: Human in the Loop Large Language Models Enabled A Search for Robotics | This research focuses on how Large Language Models (LLMs) can help with path planning for mobile embodied agents such as robots, in a human-in-the-loop and interactive manner. A novel framework named LLM A, aims to leverage the commonsense of LLMs, and the utility-optimal A is proposed to facilitate few-shot near-optimal path planning. Prompts are used to 1) provide LLMs with essential information like environment, cost, heuristics, etc.; 2) communicate human feedback to LLMs on intermediate planning results. This makes the whole path planning process a `white box' and human feedback guides LLM A to converge quickly compared to other data-driven methods such as reinforcement learning-based (RL) path planning. In addition, it makes code-free path planning practical, henceforth promoting the inclusiveness of artificial intelligence techniques. Comparative analysis against A and RL shows that LLM A is more efficient in terms of search space and achieves an on-a-par path with A and a better path than RL. The interactive nature of LLM A* also makes it a promising tool for deployment in collaborative human-robot tasks. |
| Verbosity Bias in Preference Labeling by Large Language Models | In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LLMs is alignment with humans achieved with Reinforcement Learning from Human Feedback (RLHF), as for many LLMs such as GPT-4, Bard, etc. In addition, recent studies are investigating the replacement of human feedback with feedback from other LLMs named Reinforcement Learning from AI Feedback (RLAIF). We examine the biases that come along with evaluating LLMs with other LLMs and take a closer look into verbosity bias -- a bias where LLMs sometimes prefer more verbose answers even if they have similar qualities. We see that in our problem setting, GPT-4 prefers longer answers more than humans. We also propose a metric to measure this bias. |
| Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF | Reinforcement Learning from Human Feedback (RLHF) is popular in large language models (LLMs), whereas traditional Reinforcement Learning (RL) often falls short. Current autonomous driving methods typically utilize either human feedback in machine learning, including RL, or LLMs. Most feedback guides the car agent's learning process (e.g., controlling the car). RLHF is usually applied in the fine-tuning step, requiring direct human "preferences," which are not commonly used in optimizing autonomous driving models. In this research, we innovatively combine RLHF and LLMs to enhance autonomous driving safety. Training a model with human guidance from scratch is inefficient. Our framework starts with a pre-trained autonomous car agent model and implements multiple human-controlled agents, such as cars and pedestrians, to simulate real-life road environments. The autonomous car model is not directly controlled by humans. We integrate both physical and physiological feedback to fine-tune the model, optimizing this process using LLMs. This multi-agent interactive environment ensures safe, realistic interactions before real-world application. Finally, we will validate our model using data gathered from real-life testbeds located in New Jersey and New York City. |
| Aligning Large Language Models through Synthetic Feedback | Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs such as ChatGPT. In this work, we propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations and proprietary LLMs. First, we perform reward modeling (RM) with synthetic feedback by contrasting responses from vanilla LLMs with various sizes and prompts. Then, we use the RM to simulate high-quality demonstrations to train a supervised policy and further optimize the model with reinforcement learning. Our resulting model, Aligned Language Model with Synthetic Training dataset (ALMoST), outperforms recent open-sourced models, which are trained on the outputs of InstructGPT or human-annotated demonstrations, in alignment benchmarks. In human evaluation, our model is preferred to Alpaca and Dolly-v2, 55.0% and 58.5% of the time, respectively. Further analyses demonstrate the efficacy and importance of synthetic feedback in our framework. The code is available at https://github.com/naver-ai/almost |
| The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values | Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective human preferences and values. In this paper, we survey existing approaches for learning from human feedback, drawing on 95 papers primarily from the ACL and arXiv repositories.First, we summarise the past, pre-LLM trends for integrating human feedback into language models. Second, we give an overview of present techniques and practices, as well as the motivations for using feedback; conceptual frameworks for defining values and preferences; and how feedback is collected and from whom. Finally, we encourage a better future of feedback learning in LLMs by raising five unresolved conceptual and practical challenges. |
| LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback | To democratize large language models (LLMs) to most natural languages, it is imperative to make these models capable of understanding and generating texts in many languages, in particular low-resource ones. While recent multilingual LLMs demonstrate remarkable performance in such capabilities, these LLMs still support a limited number of human languages due to the lack of training data for low-resource languages. Moreover, these LLMs are not yet aligned with human preference for downstream tasks, which is crucial for the success of LLMs in English. In this paper, we introduce xLLaMA-100 and xBLOOM-100 (collectively xLLMs-100), which scale the multilingual capabilities of LLaMA and BLOOM to 100 languages. To do so, we construct two datasets: a multilingual instruction dataset including 100 languages, which represents the largest language coverage to date, and a cross-lingual human feedback dataset encompassing 30 languages. We perform multilingual instruction tuning on the constructed instruction data and further align the LLMs with human feedback using the DPO algorithm on our cross-lingual human feedback dataset. We evaluate the multilingual understanding and generating capabilities of xLLMs-100 on five multilingual benchmarks. Experimental results show that xLLMs-100 consistently outperforms its peers across the benchmarks by considerable margins, defining a new state-of-the-art multilingual LLM that supports 100 languages. |
| A Survey on Human Preference Learning for Large Language Models | The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a wide range of contexts. Despite the numerous related studies conducted, a perspective on how human preferences are introduced into LLMs remains limited, which may prevent a deeper comprehension of the relationships between human preferences and LLMs as well as the realization of their limitations. In this survey, we review the progress in exploring human preference learning for LLMs from a preference-centered perspective, covering the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs. We first categorize the human feedback according to data sources and formats. We then summarize techniques for human preferences modeling and compare the advantages and disadvantages of different schools of models. Moreover, we present various preference usage methods sorted by the objectives to utilize human preference signals. Finally, we summarize some prevailing approaches to evaluate LLMs in terms of alignment with human intentions and discuss our outlooks on the human intention alignment for LLMs. |
| LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models | Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired answers. However, LLMs trained with SFT sometimes make simple mistakes and result in hallucinations on reasoning tasks such as question-answering. Without external feedback, it is difficult for SFT to learn a good mapping between the question and the desired answer, especially with a small dataset. This paper introduces an alternative to SFT called Natural Language Feedback for Finetuning LLMs (LaFFi). LaFFi has LLMs directly predict the feedback they will receive from an annotator. We find that requiring such reflection can significantly improve the accuracy in in-domain question-answering tasks, providing a promising direction for the application of natural language feedback in the realm of SFT LLMs. Additional ablation studies show that the portion of human-annotated data in the annotated datasets affects the fine-tuning performance. |
| Prototypical Reward Network for Data-Efficient RLHF | The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues for LLMs and complex tasks. Our proposed framework Proto-RM leverages prototypical networks to enhance reward models under limited human feedback. By enabling stable and reliable structural learning from fewer samples, Proto-RM significantly enhances LLMs' adaptability and accuracy in interpreting human preferences. Extensive experiments on various datasets demonstrate that Proto-RM significantly improves the performance of reward models and LLMs in human feedback tasks, achieving comparable and usually better results than traditional methods, while requiring significantly less data. in data-limited scenarios. This research offers a promising direction for enhancing the efficiency of reward models and optimizing the fine-tuning of language models under restricted feedback conditions. |
| IterAlign: Iterative Constitutional Alignment of Large Language Models | With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional AI (CAI) have been proposed for LLM alignment. However, these methods require either heavy human annotations or explicitly pre-defined constitutions, which are labor-intensive and resource-consuming. To overcome these drawbacks, we study constitution-based LLM alignment and propose a data-driven constitution discovery and self-alignment framework called IterAlign. IterAlign leverages red teaming to unveil the weaknesses of an LLM and automatically discovers new constitutions using a stronger LLM. These constitutions are then used to guide self-correction of the base LLM. Such a constitution discovery pipeline can be run iteratively and automatically to discover new constitutions that specifically target the alignment gaps in the current LLM. Empirical results on several safety benchmark datasets and multiple base LLMs show that IterAlign successfully improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to $13.5\%$ in harmlessness. |
| title | abstract |
|---|---|
| MRKE: The Multi-hop Reasoning Evaluation of LLMs by Knowledge Edition | Although Large Language Models (LLMs) have shown strong performance in Multi-hop Question Answering (MHQA) tasks, their real reasoning ability remains exploration. Current LLM QA evaluation benchmarks have shown limitations, including 1) data contamination, the evaluation data are potentially exposed to LLMs during the pretraining stage; and 2) ignoration of the reasoning chain evaluation. Thus we introduce an LLM MHQA evaluation benchmark, the first QA benchmark based on the new, unprecedented knowledge by editing the off-the-shelf HotpotQA dataset; Besides, we also annotate and evaluate the reasoning chain in the form of sub-questions and intermediate answers corresponding to the multi-hop questions. Specifically, based on the observation, 1) LLMs show a performance gap between the original HotpotQA and our edited data, deeming that current MHQA benchmarks have the potential risk of data contamination that hard to evaluate LLMs' performance objectively and scientifically; 2) LLMs only get a small percentage of the right reasoning chain, e.g. GPT-4 only gets 36.3\% right reasoning chain. We believe this new Multi-hop QA evaluation benchmark and novel evaluation methods will facilitate the development of trustworthy LLM evaluation on the MHQA task. |
| ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models | The unprecedented performance of large language models (LLMs) requires comprehensive and accurate evaluation. We argue that for LLMs evaluation, benchmarks need to be comprehensive and systematic. To this end, we propose the ZhuJiu benchmark, which has the following strengths: (1) Multi-dimensional ability coverage: We comprehensively evaluate LLMs across 7 ability dimensions covering 51 tasks. Especially, we also propose a new benchmark that focuses on knowledge ability of LLMs. (2) Multi-faceted evaluation methods collaboration: We use 3 different yet complementary evaluation methods to comprehensively evaluate LLMs, which can ensure the authority and accuracy of the evaluation results. (3) Comprehensive Chinese benchmark: ZhuJiu is the pioneering benchmark that fully assesses LLMs in Chinese, while also providing equally robust evaluation abilities in English. (4) Avoiding potential data leakage: To avoid data leakage, we construct evaluation data specifically for 37 tasks. We evaluate 10 current mainstream LLMs and conduct an in-depth discussion and analysis of their results. The ZhuJiu benchmark and open-participation leaderboard are publicly released at http://www.zhujiu-benchmark.com/ and we also provide a demo video at https://youtu.be/qypkJ89L1Ic. |
| OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety | The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety. |
| tinyBenchmarks: evaluating LLMs with fewer examples | The versatility of large language models (LLMs) led to the creation of diverse benchmarks that thoroughly test a variety of language models' abilities. These benchmarks consist of tens of thousands of examples making evaluation of LLMs very expensive. In this paper, we investigate strategies to reduce the number of evaluations needed to assess the performance of an LLM on several key benchmarks. For example, we show that to accurately estimate the performance of an LLM on MMLU, a popular multiple-choice QA benchmark consisting of 14K examples, it is sufficient to evaluate this LLM on 100 curated examples. We release evaluation tools and tiny versions of popular benchmarks: Open LLM Leaderboard, MMLU, HELM, and AlpacaEval 2.0. Our empirical analysis demonstrates that these tools and tiny benchmarks are sufficient to reliably and efficiently reproduce the original evaluation results. |
| How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation | In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors, the believability of LLMs among humans remains ambiguous, i.e., it is unclear which behaviors of LLMs are convincingly human-like and which need further improvements. In this work, we design SimulateBench to evaluate the believability of LLMs when simulating human behaviors. In specific, we evaluate the believability of LLMs based on two critical dimensions: 1) consistency: the extent to which LLMs can behave consistently with the given information of a human to simulate; and 2) robustness: the ability of LLMs' simulated behaviors to remain robust when faced with perturbations. SimulateBench includes 65 character profiles and a total of 8,400 questions to examine LLMs' simulated behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters. The experimental results reveal that current LLMs struggle to align their behaviors with assigned characters and are vulnerable to perturbations in certain factors. |
| Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate | Despite the utility of Large Language Models (LLMs) across a wide range of tasks and scenarios, developing a method for reliably evaluating LLMs across varied contexts continues to be challenging. Modern evaluation approaches often use LLMs to assess responses generated by LLMs. However, the meta-evaluation conducted to assess the effectiveness of these LLMs as evaluators is typically constrained by the coverage of existing benchmarks or requires extensive human annotation. This underscores the urgency of methods for scalable meta-evaluation that can effectively, reliably, and efficiently evaluate the performance of LLMs as evaluators across diverse tasks and scenarios, particularly in potentially new, user-defined scenarios. To fill this gap, we propose ScaleEval, an agent-debate-assisted meta-evaluation framework that leverages the capabilities of multiple communicative LLM agents. This framework supports multi-round discussions to assist human annotators in discerning the most capable LLMs as evaluators, which significantly eases their workload in cases that used to require large-scale annotations during meta-evaluation. We release the code for our framework, which is publicly available at: \url{https://github.com/GAIR-NLP/scaleeval}. |
| A User-Centric Benchmark for Evaluating Large Language Models | Large Language Models (LLMs) are essential tools to collaborate with users on different tasks. Evaluating their performance to serve users' needs in real-world scenarios is important. While many benchmarks have been created, they mainly focus on specific predefined model abilities. Few have covered the intended utilization of LLMs by real users. To address this oversight, we propose benchmarking LLMs from a user perspective in both dataset construction and evaluation designs. We first collect 1846 real-world use cases with 15 LLMs from a user study with 712 participants from 23 countries. These self-reported cases form the User Reported Scenarios(URS) dataset with a categorization of 7 user intents. Secondly, on this authentic multi-cultural dataset, we benchmark 10 LLM services on their efficacy in satisfying user needs. Thirdly, we show that our benchmark scores align well with user-reported experience in LLM interactions across diverse intents, both of which emphasize the overlook of subjective scenarios. In conclusion, our study proposes to benchmark LLMs from a user-centric perspective, aiming to facilitate evaluations that better reflect real user needs. The benchmark dataset and code are available at https://github.com/Alice1998/URS. |
| PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain | Biomedical language understanding benchmarks are the driving forces for artificial intelligence applications with large language model (LLM) back-ends. However, most current benchmarks: (a) are limited to English which makes it challenging to replicate many of the successes in English for other languages, or (b) focus on knowledge probing of LLMs and neglect to evaluate how LLMs apply these knowledge to perform on a wide range of bio-medical tasks, or (c) have become a publicly available corpus and are leaked to LLMs during pre-training. To facilitate the research in medical LLMs, we re-build the Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark into a large scale prompt-tuning benchmark, PromptCBLUE. Our benchmark is a suitable test-bed and an online platform for evaluating Chinese LLMs' multi-task capabilities on a wide range bio-medical tasks including medical entity recognition, medical text classification, medical natural language inference, medical dialogue understanding and medical content/dialogue generation. To establish evaluation on these tasks, we have experimented and report the results with the current 9 Chinese LLMs fine-tuned with differtent fine-tuning techniques. |
| State of What Art? A Call for Multi-Prompt LLM Evaluation | Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks. These benchmarks typically rely on a single instruction template for evaluating all LLMs on a specific task. In this paper, we comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead. We discuss tailored evaluation metrics for specific use cases (e.g., LLM developers vs. developers interested in a specific downstream task), ensuring a more reliable and meaningful assessment of LLM capabilities. We then implement these criteria and conduct evaluations of multiple models, providing insights into the true strengths and limitations of current LLMs. |
| LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond | With the recent appearance of LLMs in practical settings, having methods that can effectively detect factual inconsistencies is crucial to reduce the propagation of misinformation and improve trust in model outputs. When testing on existing factual consistency benchmarks, we find that a few large language models (LLMs) perform competitively on classification benchmarks for factual inconsistency detection compared to traditional non-LLM methods. However, a closer analysis reveals that most LLMs fail on more complex formulations of the task and exposes issues with existing evaluation benchmarks, affecting evaluation precision. To address this, we propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. This new benchmark is 20 times more cost-effective per sample than previous benchmarks and highly reproducible, as we estimate inter-annotator agreement at about 0.9. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8\% below estimated human performance, highlighting the gaps in LLMs' ability to reason about facts and detect inconsistencies when they occur. |