Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data

• URL: http://arxiv.org/abs/2511.06023v1
• Date: Sat, 08 Nov 2025 14:33:21 GMT
• Title: Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data
• Authors: Deng Yixuan, Ji Xiaoqiang,
• Abstract summary: Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes.<n>This paper proposes a Multi-Reward Group Relative Policy Optimization framework to fine-tune LLMs toward ethical and bias-free behavior.<n> Experimental results demonstrate significant reductions in bias intensity and improved alignment with non-discriminatory standards.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain limited in addressing culturally specific and multi-dimensional forms of discrimination. This paper proposes a Multi-Reward Group Relative Policy Optimization (GRPO) framework to fine-tune LLMs toward ethical and bias-free behavior. Our approach constructs a synthetic English-language dataset derived from Chinese-context discrimination categories, including regional, ethnic, and occupational biases. Each instance is paired with both neutral and biased responses to train a reward model based on DeBERTa-v3, which provides multi-dimensional reward signals capturing fairness, neutrality, and linguistic quality. The trained reward model then guides GRPO fine-tuning to optimize model outputs along these ethical dimensions. Experimental results demonstrate significant reductions in bias intensity and improved alignment with non-discriminatory standards without compromising fluency or informativeness. This study highlights the effectiveness of GRPO-based multi-reward optimization for de-biasing LLMs and offers a replicable framework for cultural-contextual ethical alignment.

Related papers

• Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation [0.0]
  Large Language models (LLMs) have gained popularity in recent years with the advancement of Natural Language Processing (NLP)<n>This study inspects and highlights the need to address biases in LLMs amid growing generative Artificial Intelligence (AI)<n>We utilize bias-specific benchmarks such StereoSet and CrowSPairs to evaluate the existence of various biases in many different generative models such as BERT, GPT 3.5, and ADA.
  arXiv  Detail & Related papers  (2025-11-18T05:43:34Z)
• A Comprehensive Study of Implicit and Explicit Biases in Large Language Models [1.0555164678638427]
  This study highlights the need to address biases in Large Language Models amid growing generative AI.<n>We studied bias-specific benchmarks such as StereoSet and CrowSPairs to evaluate the existence of various biases in multiple generative models such as BERT and GPT 3.5.<n>Results indicated fine-tuned models struggle with gender biases but excelled at identifying and avoiding racial biases.
  arXiv  Detail & Related papers  (2025-11-18T05:27:17Z)
• SESGO: Spanish Evaluation of Stereotypical Generative Outputs [1.1549572298362782]
  This paper addresses the critical gap in evaluating bias in multilingual Large Language Models (LLMs)<n>Current evaluations remain predominantly US-English-centric, leaving potential harms in other linguistic and cultural contexts largely underexamined.<n>We introduce a novel, culturally-grounded framework for detecting social biases in instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2025-09-03T14:04:51Z)
• Do Large Language Models Understand Morality Across Cultures? [0.5356944479760104]
  This study investigates the extent to which large language models capture cross-cultural differences and similarities in moral perspectives.<n>Our results reveal that current LLMs often fail to reproduce the full spectrum of cross-cultural moral variation.<n>These findings highlight a pressing need for more robust approaches to mitigate biases and improve cultural representativeness in LLMs.
  arXiv  Detail & Related papers  (2025-07-28T20:25:36Z)
• Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models [10.565316815513235]
  Large language models (LLMs) may still exhibit implicit biases when simulating human behavior.<n>We show that state-of-the-art LLMs exhibit significant sociodemographic disparities in nearly all simulations.<n>When comparing our findings to real-world disparities reported in empirical studies, we find that the biases we uncovered are directionally aligned but markedly amplified.
  arXiv  Detail & Related papers  (2025-01-29T05:21:31Z)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [91.86718720024825]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias.<n>Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning.<n>We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness [3.5297361401370044]
  This study explores the interplay between bias and LLM-based recommendation systems.<n>It focuses on music, song, and book recommendations across diverse demographic and cultural groups.<n>Our findings reveal that bias in these systems is deeply ingrained, yet even simple interventions like prompt engineering can significantly reduce it.
  arXiv  Detail & Related papers  (2024-09-17T01:37:57Z)
• Social Debiasing for Fair Multi-modal LLMs [59.61512883471714]
  Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities.<n>These models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender.<n>This paper addresses the issue of social biases in MLLMs by introducing a comprehensive counterfactual dataset with multiple social concepts.
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)
• BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization [0.0]
  Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization (DPO) to mitigate gender, racial, and religious biases in English text. By developing a loss function that favors less biased over biased completions, our approach cultivates a preference for respectful and non-discriminatory language.
  arXiv  Detail & Related papers  (2024-07-18T22:32:20Z)
• CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [58.57987316300529]
  Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks.<n>To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets.<n>We propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
  arXiv  Detail & Related papers  (2024-07-02T16:31:37Z)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.<n>We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences.<n>Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• 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)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)

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.