Multi-Persona Thinking for Bias Mitigation in Large Language Models

• URL: http://arxiv.org/abs/2601.15488v1
• Date: Wed, 21 Jan 2026 21:40:58 GMT
• Title: Multi-Persona Thinking for Bias Mitigation in Large Language Models
• Authors: Yuxing Chen, Guoqing Luo, Zijun Wu, Lili Mou,
• Abstract summary: Large Language Models (LLMs) exhibit significant social biases that can perpetuate harmful stereotypes and unfair outcomes.<n>We propose Multi-Persona Thinking (MPT), a novel inference-time framework that leverages dialectical reasoning from multiple perspectives to reduce bias.<n>MPT guides models to adopt contrasting social identities along with a neutral viewpoint, and then engages these personas iteratively to expose and correct biases.
• Score: 21.10313260260077
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) exhibit significant social biases that can perpetuate harmful stereotypes and unfair outcomes. In this paper, we propose Multi-Persona Thinking (MPT), a novel inference-time framework that leverages dialectical reasoning from multiple perspectives to reduce bias. MPT guides models to adopt contrasting social identities (e.g., male and female) along with a neutral viewpoint, and then engages these personas iteratively to expose and correct biases. Through a dialectical reasoning process, the framework transforms the potential weakness of persona assignment into a strength for bias mitigation. We evaluate MPT on two widely used bias benchmarks across both open-source and closed-source models of varying scales. Our results demonstrate substantial improvements over existing prompting-based strategies: MPT achieves the lowest bias while maintaining core reasoning ability.

Related papers

• Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models [45.41676783204022]
  We investigate various proxy measures of bias in large language models (LLMs)<n>We find that evaluating models with pre-prompted personae on a multi-subject benchmark (MMLU) leads to negligible and mostly random differences in scores.<n>With the recent trend for LLM assistant memory and personalization, these problems open up from a different angle.
  arXiv  Detail & Related papers  (2025-06-12T08:47:40Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [58.32070787537946]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge [70.89799989428367]
  We conduct a systematic analysis of four diverse bias types: position bias, verbosity bias, chain-of-thought bias, and bandwagon bias.<n>We evaluate these biases across two widely adopted multi-agent LLM-as-Judge frameworks: Multi-Agent-Debate and LLM-as-Meta-Judge.
  arXiv  Detail & Related papers  (2025-05-26T03:56:41Z)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [18.625071242029936]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content.<n>This paper presents a systematic framework to investigate and compare explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models [1.787433808079955]
  Large language models (LLMs) have been observed to perpetuate unwanted biases in training data.<n>In this paper, we mitigate bias by leveraging small biased and anti-biased expert models to obtain a debiasing signal.<n> Experiments on mitigating gender, race, and religion biases show a reduction in bias on several local and global bias metrics.
  arXiv  Detail & Related papers  (2024-12-02T16:56:08Z)
• Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion [0.40964539027092917]
  We evaluate the severity of bias toward a view by using a biased model in edge cases of excessive bias scenarios. Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness.
  arXiv  Detail & Related papers  (2024-08-15T15:23:00Z)
• Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective [66.34066553400108]
  We conduct a rigorous evaluation of large language models' implicit bias towards certain demographics.<n>Inspired by psychometric principles, we propose three attack approaches, i.e., Disguise, Deception, and Teaching.<n>Our methods can elicit LLMs' inner bias more effectively than competitive baselines.
  arXiv  Detail & Related papers  (2024-06-20T06:42:08Z)
• GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models [83.30078426829627]
  Large language models (LLMs) have gained popularity and are being widely adopted by a large user community. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
  arXiv  Detail & Related papers  (2023-12-11T12:02:14Z)
• Cognitive bias in large language models: Cautious optimism meets anti-Panglossian meliorism [0.0]
  Traditional discussions of bias in large language models focus on a conception of bias closely tied to unfairness. Recent work raises the novel possibility of assessing the outputs of large language models for a range of cognitive biases. I draw out philosophical implications of this discussion for the rationality of human cognitive biases as well as the role of unrepresentative data in driving model biases.
  arXiv  Detail & Related papers  (2023-11-18T01:58:23Z)
• The SAME score: Improved cosine based bias score for word embeddings [49.75878234192369]
  We introduce SAME, a novel bias score for semantic bias in embeddings. We show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
  arXiv  Detail & Related papers  (2022-03-28T09:28:13Z)
• Towards Understanding and Mitigating Social Biases in Language Models [107.82654101403264]
  Large-scale pretrained language models (LMs) can be potentially dangerous in manifesting undesirable representational biases. We propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information.
  arXiv  Detail & Related papers  (2021-06-24T17:52:43Z)

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.