Demographic Bias in Language Models

Ask about this topic

Overview

This field examines whether language models treat people differently because of demographic cues such as names, dialects, race, gender, age, disability, or socioeconomic status. Researchers use counterfactual prompts, demographic benchmarks, comparisons with human judgments, and audits of high-stakes tasks such as hiring, health care, education, and recommendations; some also probe model internals to trace how identity affects behavior. Mitigation approaches include prompt design, fine-tuning, representation editing, retrieval, and changes to annotation or decision workflows. A central challenge is that aggregate accuracy or fair-looking outputs can hide intersectional disparities or biased internal signals, while interventions can trade off fairness against utility, personalization, and faithful representation of individuals.

Latest papers

CardsList

135 papers21 papers in the last four weeks, up 24% on the four weeks before. 0.1% of all new papers.

  1. How AI Writing Assistance Distorts Perceptions of AI Users and Their Opinions

    Apr 24, 2026Paul Röttger, Kobi Hackenburg, Hannah Rose Kirk +1Trust in AIDemographic Bias in Language Models

    University of Oxford · UK AI Security Institute

  2. From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation

    Apr 23, 2026Minh Duc Bui, Xenia Heilmann, Mattia Cerrato +2Algorithmic BiasCode Generation Evaluation

    Johannes Gutenberg University Mainz, Germany · Universidad Iberoamericana, Ciudad de Mexico · University of Colorado Boulder, USA

  3. Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles

    Apr 22, 2026Irti Haq, Belén SaldíasLanguage Model Safety EvaluationSocial Bias in Language Models

    University of Washington, USA

  4. Intersectional Fairness in Large Language Models

    Apr 22, 2026Chaima Boufaied, Ronnie De Souza Santos, Ann BarcombAlgorithmic FairnessLanguage Model Bias Evaluation

    University of Calgary, Calgary, Canada

  5. Surrogate modeling for interpreting black-box LLMs in medical predictions

    Apr 22, 2026Changho Han, Songsoo Kim, Dong Won Kim +4Surrogate ModelingLLM Interpretability

    Medical Big Data Research Center, Seoul National University Medical Research Center, Seoul National University College of Medicine, Seoul, Republic of Korea · Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea. · Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA 02139 +5

  6. Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives

    Apr 22, 2026Melanie Subbiah, Haaris Mian, Nicholas Deas +3Gender Bias in Language ModelsLLM Auditing

    Department of Computer Science, Columbia University · Department of Applied Physics and Applied Mathematics, Columbia University · Department of Psychology, Northwestern University

  7. Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring

    Apr 21, 2026Huy Nghiem, Phuong-Anh Nguyen-Le, Sy-Tuyen Ho +1Algorithmic BiasLanguage Model Bias Evaluation

    University of Maryland

  8. PsychBench: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations

    Apr 19, 2026Patrick KeoughHealthcareLLM Auditing

    Independent Researcher Bremerton, Washington, USA

  9. Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA

    Apr 19, 2026Alberto Testoni, Iacer CalixtoIntersectional Bias in Language ModelsHealthcare

    Department of Medical Informatics, Amsterdam University Medical Center, University of Amsterdam, Amsterdam, The Netherlands. · Amsterdam Public Health, Methodology, Amsterdam, The Netherlands.

  10. Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration

    Apr 15, 2026Sayan Kumar Chaki, Antoine Gourru, Julien VelcinDemographic Bias in Language ModelsMulti-Agent Systems

    Laboratoire Hubert Curien, UMR CNRS 5516, Saint-Étienne, France · École Centrale de Lyon, LIRIS CNRS UMR 5205

  11. Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models

    Apr 13, 2026Benjamin Maltbie, Shivam RavalIntersectional Bias in Language ModelsLLM Sycophancy

    Massachusetts Institute of Technology, Cambridge, MA, USA · Harvard University, Cambridge, MA, USA

  12. Nationality encoding in language model hidden states: Probing culturally differentiated representations in persona-conditioned academic text

    Apr 11, 2026Paul Jackson, Ruizhe Li, Elspeth EdelsteinDemographic Bias in Language ModelsCross-Cultural Language Model Evaluation

    Language Centre, School of Language, Literature, Music and Visual Culture, University of Aberdeen, United Kingdom · Language Centre, School of Language, Literature, Music and Visual Culture, University of Aberdeen, Aberdeen AB24 3FX, United Kingdom. · School of Natural and Computing Sciences, University of Aberdeen, United Kingdom +3

  13. Digital Skin, Digital Bias: Uncovering Tone-Based Biases in LLMs and Emoji Embeddings

    Apr 8, 2026Mingchen Li, Wajdi Aljedaani, Yingjie Liu +5Demographic Bias in Language ModelsLanguage Model Bias Evaluation

    University of North Texas Denton, TX, United States · International Center for Artificial Intelligence Research and Ethics Riyadh, Saudi Arabia · Southern Methodist University Dallas, TX, United States +2

  14. Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning

    Apr 7, 2026Yanbei Jiang, Amr Keleg, Ryandito Diandaru +4LLM AlignmentLLM Fine-Tuning

    University of Melbourne · Mohamed bin Zayed University of Artificial Intelligence · Oracle

  15. Attribution Bias in Large Language Models

    Apr 6, 2026Eliza Berman, Bella Chang, Daniel B. Neill +1Claim Attribution in Language ModelsSocial Bias in Language Models

    New York University

  16. Sociodemographic Biases in Educational Counselling by Large Language Models

    Apr 3, 2026Tomasz Adamczyk, Wiktoria Mieleszczenko-Kowszewicz, Beata Bajcar +6Demographic Bias in Language ModelsLanguage Model Bias Evaluation

    Wrocław University of Science and Technology, Wrocław, Poland · University of Silesia in Katowice, Katowice, Poland

  17. SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models

    Apr 3, 2026Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur +3Social Bias in Language ModelsLanguage Model Bias Evaluation

    Enkrypt AI

  18. ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

    Apr 2, 2026Bhaskara Hanuma Vedula, Darshan Anghan, Ishita Goyal +2Social Bias in Language ModelsLanguage Model Bias Evaluation

    International Institute of Information Technology, Hyderabad · Indian Institute of Technology, Kharagpur

  19. Limited Stereotype Control Through Routing Reweighting in MoE Language Models

    Mar 28, 2026Junhyeok Lee, Han Jang, Kyu Sung ChoiSocial Bias in Language ModelsDemographic Bias in Language Models

    Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine · Department of Radiology, Seoul National University Hospital · Department of Radiology, Seoul National University College of Medicine +1

  20. Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters

    Mar 24, 2026Nan Cui, Wendy Hui Wang, Yue NingFairness in Recommender SystemsDemographic Bias in Language Models

    Department of Computer Science, Stevens Institute of Technology, Hoboken NJ, USA

  21. Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts

    Mar 24, 2026Maida Aizaz, Quang Minh NguyenPolitical Bias in Language ModelsDemographic Bias in Language Models

    Graduate School of Data Science KAIST

  22. CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs

    Mar 23, 2026Ravi Ranjan, Utkarsh Grover, Mayur Akewar +2Language Model DebiasingSocial Bias in Language Models

    Florida International University Miami, USA · University of South Florida Tampa, USA

  23. Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks

    Mar 22, 2026Navya Mehrotra, Adam Visokay, Kristina GligorićAnnotator DisagreementLLM-Assisted Annotation

    University of Washington

  24. UGID: Unified Graph Isomorphism for Debiasing Large Language Models

    Mar 19, 2026Zikang Ding, Junchi Yao, Junhao Li +4Language Model DebiasingSocial Bias in Language Models

    University of Electronic Science and Technology of China, Chengdu, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · South China University of Technology, Guangzhou, China

  25. Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation

    Mar 14, 2026Petter TörnbergSocial Bias in Language ModelsDemographic Bias in Language Models

    Institute for Logic, Language and Computation (ILLC), University of Amsterdam„ Science Park 107, 1098 XG Amsterdam, Netherlands

  26. Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback

    Mar 12, 2026Mei Tan, Lena Phalen, Dorottya DemszkyLinguistic Bias in Language ModelsDemographic Bias in Language Models

    Stanford University, Stanford, California, USA

  27. Towards a more efficient bias detection in financial language models

    Mar 9, 2026Firas Hadj Kacem, Ahmed Khanfir, Mike PapadakisFinancial Language Model EvaluationIntersectional Bias in Language Models

    SnT, University of Luxembourg, Luxembourg · RIADI, ENSI, University of Manouba, Tunisia

  28. Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness

    Mar 7, 2026Ravi Ranjan, Utkarsh Grover, Agorista PolyzouSocial Bias in Language ModelsDemographic Bias in Language Models

    Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL 33199 · College of Engineering, University of South Florida, Tampa, FL 33620

  29. Measuring What VLMs Don't Say: Validation Metrics Hide Clinical Terminology Erasure in Radiology Report Generation

    Mar 2, 2026Aditya Parikh, Aasa Feragen, Sneha Das +1VLM EvaluationRadiology Report Evaluation

    DTU Compute, Technical University of Denmark

  30. Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs

    Feb 28, 2026Yiran Zhao, Lu Zhou, Xiaogang Xu +3Algorithmic FairnessDemographic Bias in Language Models

    Nanjing University of Aeronautics and Astronautics · Collaborative Innovation Center of Novel Software Technology and Industrialization · The Chinese University of Hong Kong +2