Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs
- URL: http://arxiv.org/abs/2404.10160v5
- Date: Tue, 18 Jun 2024 16:19:40 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 find that involving LLMs in role-playing scenario boosts their ability to recognize and mitigate biases.
We propose Reinforcement Learning from Multi-role Debates as Feedback (RLDF), a novel approach for bias mitigation replacing human feedback.
- 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 demonstrate the effectiveness of our approach in bias mitigation.
Related papers
- Supporting Self-Reflection at Scale with Large Language Models: Insights from Randomized Field Experiments in Classrooms [7.550701021850185]
We investigate the potential of Large Language Models (LLMs) to help students engage in post-lesson reflection.
We conducted two randomized field experiments in undergraduate computer science courses.
arXiv Detail & Related papers (2024-06-01T02:41:59Z) - 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) - Large Language Models are Inconsistent and Biased Evaluators [2.136983452580014]
We show that Large Language Models (LLMs) are biased evaluators as they exhibit familiarity bias and show skewed distributions of ratings.
We also found that LLMs are inconsistent evaluators, showing low "inter-sample" agreement and sensitivity to prompt differences that are insignificant to human understanding of text quality.
arXiv Detail & Related papers (2024-05-02T20:42:28Z) - Exploring Value Biases: How LLMs Deviate Towards the Ideal [57.99044181599786]
Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact.
We show that value bias is strong in LLMs across different categories, similar to the results found in human studies.
arXiv Detail & Related papers (2024-02-16T18:28:43Z) - 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) - Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools.
Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions.
Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
arXiv Detail & Related papers (2023-09-20T09:23:46Z) - Rethinking Learning Rate Tuning in the Era of Large Language Models [11.87985768634266]
Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance.
It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world applications.
Existing learning rate policies are primarily designed for training traditional deep neural networks (DNNs)
arXiv Detail & Related papers (2023-09-16T03:37:00Z) - 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.