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. SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context

    Feb 25, 2026Aishwarya Verma, Laud Ammah, Olivia Nercy Ndlovu Lucas +3Demographic Bias in Language ModelsLow-Resource Language Processing

    Google Research · RAIN Africa · Mantaray Africa

  2. Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance System

    Feb 16, 2026Kawin Mayilvaghanan, Siddhant Gupta, Ayush KumarLanguage Model Bias EvaluationDemographic Bias in Language Models

    Observe.AI Bangalore, India

  3. Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement

    Jan 29, 2026Jinhao Pan, Chahat Raj, Anjishnu Mukherjee +4Debiased MLSocial Bias in Language Models

    Department of Computer Science, George Mason University, Fairfax, VA, USA · Lightridge High School, Aldie, VA, USA

  4. Large Language Models Naively Recover Ethnicity from Individual Records

    Jan 29, 2026Noah DasanaikeLLM InferenceDemographic Bias in Language Models

    PhD Candidate, Department of Government, Harvard University

  5. Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

    Jan 19, 2026Shiyue Hu, Ruizhe Li, Yanjun GaoLLM InterpretabilityMechanistic Interpretability

    University of Colorado Anschutz · University of Colorado Boulder · University of Aberdeen

  6. Safety Is Not Universal: The Selective Safety Trap in LLM Alignment

    Jan 7, 2026Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2LLM Safety BenchmarksLLM Alignment

    Advanced Knowledge Center for Immersive Technologies (AKCIT) Federal University of Goiás (UFG)

  7. Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

    Jan 6, 2026David Hartmann, Lena Pohlmann, Lelia Hanslik +3LLM AuditingAlgorithmic Fairness

    Weizenbaum Institut Berlin · Technische Universität Berlin · FIZ Karlsruhe +2

  8. Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Prompting

    Dec 17, 2025Gangxiong Zhang, Yongchao Long, Yuxi Zhou +2Algorithmic FairnessFew-Shot Prompting

    School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China · Institute for Artificial Intelligence, Peking University, Beijing, China · DCST, BNRist, RIIT, Institute of Internet Industry, Tsinghua University, Beijing, China +1

  9. Behavioral Coherence: A Method for Sensitive-Domain LLM Evaluation

    Dec 15, 2025Anika Sharma, Malavika Mampally, Chidaksh Ravuru +2Language Model Bias EvaluationDemographic Bias in Language Models

    Society-Centered AI Lab UNC Chapel Hill, USA · School of Nursing UNC Chapel Hill, USA

  10. Large Language Models Develop Novel Social Biases Through Adaptive Exploration

    Nov 8, 2025Addison J. Wu, Ryan Liu, Xuechunzi Bai +1Social Bias in Language ModelsLanguage Model Bias Evaluation

    1Princeton University · University

  11. ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

    Oct 13, 2025Mahika Phutane, Hayoung Jung, Matthew Kim +2Intersectional Bias in Language ModelsSocial Bias in Language Models

    Cornell University · Princeton University · University of Washington

  12. Unequal Voices: How LLMs Construct Constrained Queer Narratives

    Jul 21, 2025Atreya Ghosal, Ashim Gupta, Vivek SrikumarSocial Bias in Language ModelsDemographic Bias in Language Models

    University of Utah

  13. In-Context Bias Propagation in LLM-Based Tabular Data Generation

    Jun 11, 2025Pol G. Recasens, Alberto Gutierrez, Jordi Torres +4Synthetic Data GenerationSynthetic Tabular Data Generation

    Barcelona Supercomputing Center (BSC), Spain · Universitat Politècnica de Catalunya (UPC), Spain · IBM Research Ireland

  14. Which Demographics do LLMs Default to During Annotation?

    Oct 11, 2024Johannes Schäfer, Aidan Combs, Christopher Bagdon +9LLM PromptingLLM-Assisted Annotation

    Fundamentals of Natural Language Processing, University of Bamberg, Germany

  15. Fairness Definitions in Language Models Explained

    Jul 26, 2024Zhipeng Yin, Zichong Wang, Avash Palikhe +1Social Bias in Language ModelsDemographic Bias in Language Models

    Florida International University, Miami, USA