Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs

• URL: http://arxiv.org/abs/2404.10160v6
• Date: Fri, 16 Aug 2024 12:20:22 GMT
• Title: Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs
• Authors: Ruoxi Cheng, Haoxuan Ma, Shuirong Cao, Jiaqi Li, Aihua Pei, Zhiqiang Wang, Pengliang Ji, Haoyu Wang, Jiaqi Huo,
• Abstract summary: We propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF. We utilize LLMs in multi-role debates to create a dataset that includes both high-bias and low-bias instances for training the reward model in reinforcement learning.
• Score: 6.090496490133132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bias in LLMs can harm user experience and societal outcomes. However, current bias mitigation methods often require intensive human feedback, lack transferability to other topics or yield overconfident and random outputs. We find that involving LLMs in role-playing scenario boosts their ability to recognize and mitigate biases. Based on this, we propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback in traditional RLHF. We utilize LLMs in multi-role debates to create a dataset that includes both high-bias and low-bias instances for training the reward model in reinforcement learning. Our approach comprises two modes: (1) self-reflection, where the same LLM participates in multi-role debates, and (2) teacher-student, where a more advanced LLM like GPT-3.5-turbo guides the LLM to perform this task. Experimental results across different LLMs on BBQ and our datasets demonstrate the effectiveness of our approach in bias mitigation. Our source code and datasets are available at \texttt{https://anonymous.4open.science/r/RLDF-E344}.

Related papers

• Benchmarking Bias in Large Language Models during Role-Playing [21.28427555283642]
  We introduce BiasLens, a fairness testing framework designed to expose biases in Large Language Models (LLMs) during role-playing. Our approach uses LLMs to generate 550 social roles across a comprehensive set of 11 demographic attributes, producing 33,000 role-specific questions. Using the generated questions as the benchmark, we conduct extensive evaluations of six advanced LLMs released by OpenAI, Mistral AI, Meta, Alibaba, and DeepSeek. Our benchmark reveals 72,716 biased responses across the studied LLMs, with individual models yielding between 7,754 and 16,963 biased responses.
  arXiv  Detail & Related papers  (2024-11-01T13:47:00Z)
• A Multi-LLM Debiasing Framework [85.17156744155915]
  Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Recent research has shown a growing interest in multi-LLM approaches, which have been demonstrated to be effective in improving the quality of reasoning. We propose a novel multi-LLM debiasing framework aimed at reducing bias in LLMs.
  arXiv  Detail & Related papers  (2024-09-20T20:24:50Z)
• Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study [14.906150451947443]
  We study two many-shot ICL prompts for helping evaluators to mitigate the potential biases in Large Language Models (LLMs) Based on the designed prompts, we investigate the impact of scaling the number of in-context examples on the consistency and quality of the evaluation results. Experimental results show that advanced LLMs, such as GPT-4o, perform better in the many-shot regime than in the zero-shot regime.
  arXiv  Detail & Related papers  (2024-06-17T15:11:58Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves [57.974103113675795]
  We present a method named Rephrase and Respond' (RaR) which allows Large Language Models to rephrase and expand questions posed by humans. RaR serves as a simple yet effective prompting method for improving performance. We show that RaR is complementary to the popular Chain-of-Thought (CoT) methods, both theoretically and empirically.
  arXiv  Detail & Related papers  (2023-11-07T18:43:34Z)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• Verbosity Bias in Preference Labeling by Large Language Models [10.242500241407466]
  We examine the biases that come along with evaluating Large Language Models (LLMs) We take a closer look into verbosity bias -- a bias where LLMs sometimes prefer more verbose answers even if they have similar qualities.
  arXiv  Detail & Related papers  (2023-10-16T05:19:02Z)
• A Survey on Fairness in Large Language Models [28.05516809190299]
  Large Language Models (LLMs) have shown powerful performance and development prospects. LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms.
  arXiv  Detail & Related papers  (2023-08-20T03:30:22Z)
• On Learning to Summarize with Large Language Models as References [101.79795027550959]
  Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
  arXiv  Detail & Related papers  (2023-05-23T16:56:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.