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. AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases

    Oct 23, 2026Yi Qi, Srijoni Majumdar, Evangelos PournarasDemographic Bias in Language ModelsLLM Alignment

    University of Leeds Leeds, United Kingdom

  2. Which Answer Did the Seventeen-Year-Old Write? A Behavioral Case Study of Author-Age Misattribution, Miscalibrated Confidence, and Non-Corrective Self-Explanation in Six Frontier Language Models

    Oct 22, 2026Brianne LeeDemographic Bias in Language ModelsLanguage Model Self-Assessment

    Independent Researcher

  3. Invisibilization as a Source of Probability Bias in Language Models

    Oct 22, 2026Christian Arnold, Ernesto Calvo, Guadalupe Gonzalez +2Demographic Bias in Language ModelsLanguage Model Bias Evaluation

    University of Birmingham · University of Maryland, College Park · University of Western Ontario +1

  4. Do LLMs Reproduce the Age Gap in Loneliness? Evaluating Survey Simulation against European Survey Data

    Oct 18, 2026Yuliya Li, Achim Rettinger, Dominik BeyerLarge Language Model-Based Social SimulationDemographic Bias in Language Models

    Trier University, Germany · FZI Research Center for Information Technology, Karlsruhe, Germany

  5. Aligning Language Models Towards Counterfactual Invariance

    Oct 16, 2026Basar Demir, Emily Shen, Ksheeraj Sai Vepuri +5Demographic Bias in Language ModelsCounterfactual Fairness

    Meta Superintelligence Labs · University of California, San Diego · Independent Researcher

  6. Mitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization

    Oct 15, 2026Suryansh Talukdar, Taha Sarwat, Jonathan RusertDemographic Bias in Language ModelsFaithfulness of Language Model Explanations

    Purdue University Fort Wayne

  7. Name-Bias in Large Language Models

    Oct 15, 2026Kalyan Bhetwal, Ceren Mert, Ian WhitehouseSocial Bias in Language ModelsDemographic Bias in Language Models

    University of Maryland, College Park, USA

  8. Are AI Decision Models Biased? A Case Study of Jev

    Oct 14, 2026Ilaria Imperatrice, Taisia Kameneva, Adam Eric Greenberg +1Cognitive Bias in Language ModelsLLM Decision-Making

    Bocconi University

  9. Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment

    Oct 11, 2026Alex Martí Guiu, Nicolas Zumarraga, Kevin O'Sullivan +2Emergent Misalignment in Language ModelsLanguage Model Safety Evaluation

    Agentic Systems Lab, ETH Zurich · ETH AI Center, ETH Zurich

  10. Who Receives Respect? A Counterfactual Benchmark for Honorific Allocation Bias in Bengali

    Oct 10, 2026Ajwad Abrar, Md Kamrul Hasan, Hasan MahmudLanguage Model Bias EvaluationDemographic Bias in Language Models

    Systems and Software Lab, Department of Computer Science and Engineering, Islamic University of Technology, Gazipur, Bangladesh

  11. Thin Evidence, Thick Priors: How Language Models Substitute Identity for Missing Financial Facts

    Oct 6, 2026Saanvi Khetan, Sankar BalasubramanianDemographic Bias in Language ModelsLLM Auditing

    The International School, Bangalore · Indian Institute of Science (IISc), Bangalore

  12. A Systematic Investigation of Bias in Large Language Models for Advertising Relevance

    Oct 6, 2026Weiwei Wang, Yinchuan Xu, Jialu Gao +2Bias in LLM-as-a-JudgeLanguage Model Bias Evaluation

    Microsoft

  13. Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering

    Oct 5, 2026Sarim Hashmi, Mukul Ranjan, Abdelrahman Elsayed +3Adversarial Attacks on Diffusion ModelsDiffusion Language Models

    Mohamed bin Zayed University of Artificial Intelligence

  14. Collective Bias Mitigation via Model Routing and Collaboration

    Oct 2, 2026Mingzhe Du, Luu Anh Tuan, Xiaobao Wu +7Social Bias in Language ModelsDemographic Bias in Language Models

    Nanyang Technological University · National University of Singapore · Harbin Institute of Technology +1

  15. Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage

    Oct 1, 2026Manar Aljohani, Brandon Ho, Kenneth McKinley +2Clinical Decision-MakingLanguage Model Bias Evaluation

    Department of Computer Science Virginia Tech Blacksburg, VA, US · Division of Emergency Medicine University of Washington and Seattle Children’s Hospital Seattle, WA, USA · Children’s National Hospital Washington DC, USA

  16. Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs

    Sep 29, 2026Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi ShekharLLM PruningAlgorithmic Fairness

    School of Computer Science and Electronic Engineering, University of Essex, UK

  17. Calibrated to Whom? Persona and Language Effects on Cultural Values in JEV

    Sep 28, 2026Bushra Asseri, Abdulaziz AsseriMultilingual Language Model EvaluationCross-Cultural Language Model Evaluation

    College of Engineering and Advanced Computing, Alfaisal University, Riyadh, Saudi Arabia · Proxa.sa, Riyadh, Saudi Arabia

  18. Population Fidelity: Evaluating Population Representativeness in LLMs

    Sep 28, 2026Neemias B. da Silva, Martin Lukk, Ali Sutani +5LLM EvaluationLLM Fine-Tuning

    University of Toronto, Canada · Federal University of Technology – Paran´a, Brazil

  19. HEAR: Real Voices, Real Bias: A Large-Scale Human-Recorded, Demographically Diverse Benchmark for Audio Language Models

    Sep 28, 2026Shen Yan, Duc Le, Irina-Elena VelicheAudio-Language Model EvaluationAudio-Language Models

    Meta Superintelligence Labs

  20. BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment

    Sep 28, 2026Antonio Ferrara, Alberto Rumi, Francesco BonchiLLM AlignmentDebiased ML

    Intesa Sanpaolo AI Research

  21. Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models

    Sep 28, 2026Mir Tafseer Nayeem, Davood RafieiLLM InterpretabilityLanguage Model Bias Evaluation

    Department of Computing Science University of Alberta

  22. Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs

    Sep 26, 2026Chaitali Deb Purkayastha, Bharath Kumar Bolla, Vishnu Surya Reddy NandiClinical Language Model EvaluationLanguage Model Robustness

    Independent Researcher, Bengaluru · The Institute of Product Leadership, Bengaluru, India · Amazon, Seattle, US

  23. RupeeBias: Auditing Demographic Bias in Indian Economic Guidance from Large Language Models

    Sep 25, 2026Pavithra P M Nair, Bhavik Talaviya, Shourya Bhushan +5Language Model Bias EvaluationDemographic Bias in Language Models

    Center for Cybersecurity Systems & Networks, Amrita Vishwa Vidyapeetham, Amritapuri, India · Unique Identification Authority of India, Delhi, India

  24. Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More

    Sep 25, 2026Deng Pan, Joe Germino, Yihong Ma +4Social Bias in Language ModelsLanguage Model Bias Evaluation

    University of Notre Dame · IBM Research, Dublin

  25. White Men Without Degrees Receive the Lowest Ratings from Large Language Models

    Sep 17, 2026Maxim ChupilkinDemographic Bias in Language ModelsLanguage Model Bias Evaluation

    Department of Politics and International Relations, University of Oxford, Oxford, United Kingdom

  26. Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence

    Sep 17, 2026Yutong Yao, Yanjie Cao, Guanhua Chen +5Abductive ReasoningLegal Judgment Prediction

    NLP2CT Lab, Faculty of Information Science and Computing, University of Macau · Faculty of Social Sciences, University of Macau

  27. Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

    Sep 16, 2026Kosuke Kitahara, Nobuhiro YamaguchiGender Bias in Language ModelsAI-Assisted Decision Making

    Recruit Co., Ltd. 1-9-2 Marunouchi Chiyoda-ku, Tokyo 100-6640 Japan

  28. The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment

    Sep 15, 2026Donya Rooein, Luca Benedetto, Dirk HovyAI in EducationGenerative AI in Education

    Bocconi University, Milan, Italy · Télécom SudParis, Institut Polytechnique de Paris, Palaiseau, France

  29. Beyond the Name: Demographic Leakage in De-Identified Résumés and Evaluation Artifacts in LLM Bias Audits

    Sep 15, 2026Qiangju Chen, Yang XiaoLLM-as-a-JudgeLanguage Model Bias Evaluation

    Macquarie University · The University of Melbourne

  30. EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student Demographics

    Sep 11, 2026Jiaxu Zhao, Bahar Radmehr, Fares Fawzi +2Generative AI in EducationLanguage Model Bias Evaluation

    Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland