Social Bias in Language Models

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 44% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 126

All topics

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization
Jun 3, 2026Saket Reddy, Ke Yang, ChengXiang ZhaiReward Modeling RL for Language Models
University of Illinois - Urbana-Champaign
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
Jun 1, 2026Vera Neplenbroek, Gabriele Sarti, Arianna Bisazza +1Social Bias in Language Models Language Modeling
Institute for Logic, Language and Computation, University of Amsterdam · Khoury College of Computer Sciences, Northeastern University · Center for Language and Cognition, University of Groningen
Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents
Jun 1, 2026Aitor Arronte Alvarez, Naiyi Xie FinchamIntelligent Tutoring Systems Social Bias in Language Models
University of Hawaii at Manoa, Honolulu HI 96822, USA
COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
May 28, 2026Arya Fayyazi, Mehdi Kamal, Massoud PedramSocial Bias in Language Models Counterfactual Fairness
Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA.
Human-like in-group bias in instruction-tuned language model agents
May 27, 2026Messi H. J. LeeSocial Bias in Language Models Large Language Model-Based Social Simulation
Independent Researcher · Seoul, South Korea
Auditing Stance Asymmetry in Generative Explanations
May 27, 2026Jiarui HanLanguage Model Generation Evaluation Social Bias in Language Models
Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication
May 26, 2026Naba Rizvi, Mohammed Rizvi, Harper Strickland +2Autism Spectrum Disorder Social Bias in Language Models
University of California · Georgia Institute of Technology · Cardiff University
Side-by-side Comparison Amplifies Dialect Bias in Language Models
May 23, 2026Kritee Kondapally, Claire J. Smerdon, Pooja C. Patel +5Social Bias in Language Models Algorithmic Fairness
University of Southern California, USA
Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making
May 23, 2026David Wingate, Sheryl Carty, Joshua Coates +13Moral Reasoning in Language Models Social Bias in Language Models
1Brigham Young University · 2B. H. Roberts Foundation · 5Yeshiva University +2
When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance
May 21, 2026Brett Israelsen, Sheryl Carty, Josh Coates +3Social Bias in Language Models Language Model Bias Evaluation
Brigham Young University · B. H. Roberts Foundation
Reducing Political Manipulation with Consistency Training
May 21, 2026Long Phan, Devin Kim, Alexander Pan +3Social Bias in Language Models Political Bias in Language Models
Center for AI Safety · UC Berkeley
Occupational Prompting Reveals Cultural Bias in Large Language Models
May 19, 2026Maksim E. Eren, Andrea Brennen, Ryan C. Barron +1LLM Prompting Social Bias in Language Models
Computational Intelligence & Modeling, Los Alamos National Laboratory, Los Alamos, New Mexico, USA. · IQT, USA. · Advanced Research in Cyber Systems, Los Alamos National Laboratory, Los Alamos, New Mexico, USA.
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
May 17, 2026Jen-tse Huang, Didi Zhou, Faith Kamau +5Social Bias in Language Models Clinical Language Model Evaluation
1Johns Hopkins University.
GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models
May 16, 2026Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta +1LLM Evaluation LLM Auditing
Clark Atlanta University · United International University
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation
May 15, 2026Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6Retrieval-Augmented Generation Debiased ML
When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method
May 13, 2026Sai Hemanth Kilaru, Sriram Theerdh Manikyala, Raghav Upadhyay +3LLM Prompting Social Bias in Language Models
University of Arizona. Tucson, AZ 85721
DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models
May 12, 2026Eugenia Kim, Ioana Tanase, Christina MallonLLM Safety Benchmarks LLM Evaluation
Microsoft
Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science
May 12, 2026Varun KotteSocial Bias in Language Models LLM-Assisted Annotation
Independent Researcher
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
May 11, 2026Charlotte Park, Kate Donahue, Manish RaghavanSocial Bias in Language Models Algorithmic Fairness
Massachusetts Institute of Technology Cambridge, Massachusetts, USA
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
May 11, 2026Eduardo Tenorio, Karuna Bhaila, Xintao WuSocial Bias in Language Models Language Model Bias Evaluation
University of Arkansas
Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics
May 11, 2026Cristiano De NobiliMulti-Agent LLM Systems Multi-Agent Coordination
Critiqality, Milan, Italy
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
May 11, 2026Pierre Le Jeune, Étienne Duchesne, Weixuan Xiao +4Open-Ended Generation Multilingual Language Model Evaluation
Giskard AI · École Normale Supérieure, INSERM, Paris
Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain
May 9, 2026Xiaoyu Hu, Jinman ZhaoLLM Evaluation Social Bias in Language Models
Rutgers University · Department of Computer Science, University of Toronto
Misaligned by Reward: Socially Undesirable Preferences in LLMs
May 6, 2026Gayane Ghazaryan, Esra DönmezReward Modeling Language Model Safety Evaluation
Institute for Natural Language Processing, University of Stuttgart · 2Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart
EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage
May 5, 2026Richard J. Young, Alice M. MatthewsGender Bias in Language Models Clinical Triage
University of Nevada, Las Vegas, Lee Business School, Las Vegas, NV, USA · DeepNeuro AI, Las Vegas, NV, USA · Concorde Career Colleges, Dept. of Cardiovascular and Medical Diagnostic Sonography
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
May 4, 2026Yash Aggarwal, Atmika Gorti, Vinija Jain +3Moral Reasoning in Language Models Social Bias in Language Models
University of Maryland, College Park · 2Purdue University · 3Meta +5
Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation
May 4, 2026Muneeb Ur Raheem KhanDebiased ML Language Model Decoding
Lahore University of Management Sciences (LUMS)
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
May 2, 2026Shijun Lei, Hongyu Wang, Yunji Liang +3Knowledge Conflicts in Language Models Social Bias in Language Models
Northwestern Polytechnical University · Central University of Finance and Economics
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
May 2, 2026Plawan Kumar Rath, Rahul MaliakkalLLM Quantization Social Bias in Language Models
Meta
Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI
May 2, 2026Plawan Kumar Rath, Rahul MaliakkalLLM Pruning On-Device Language Model Inference
Meta

Jun 3, 2026, cs.AIJ/K move · Enter open · S save

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

Saket Reddy, Ke Yang, ChengXiang Zhai

University of Illinois - Urbana-Champaign

Reward Modeling RL for Language Models LLM Alignment Social Bias in Language Models Group Relative Policy Optimization

Open paper AskPDF arXiv

Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training instability due to potentially unreliable critic estimates. In this paper, we propose BiasGRPO, a framework using Group Relative Policy Optimization (GRPO) to stabilize alignment by normalizing rewards across a group of sampled completions. By substituting the value function with a group-relative baseline, our approach reduces instability while maintaining the exploration benefits of online training. We find that BiasGRPO outperforms DPO and PPO across multiple benchmarks, indicating its effectiveness. To adapt GRPO, we synthetically extend a dataset spanning multiple domains and contexts. We also create and release a custom bias reward model that effectively guides generation while being highly compute-efficient and avoiding knowledge degradation, providing a valuable resource that can be seamlessly integrated into multi-objective RLHF pipelines.

Momentum

Related topics

Latest papers 126