Cultural Bias in Language Models

Ask about this topic

Overview

Cultural bias research asks whether language models represent and respond to different communities’ knowledge, values, identities, and social norms fairly, rather than defaulting to dominant or English-language perspectives. Researchers build locally authored multilingual benchmarks and compare model answers, generated stories, safety decisions, and survey-style value distributions with native-speaker judgments and population data. Mitigation approaches include culturally grounded training and retrieval, persona or prompt conditioning, preference calibration, and activation-level steering, alongside audits of data and post-training. A central tension is that models may know culturally relevant facts but fail to apply them, while stronger alignment can flatten within-culture diversity or impose stereotypes; reliable measurement across languages and contexts remains difficult.

Latest papers

CardsList

129 papers9 papers in the last four weeks, down 25% on the four weeks before. 0.1% of all new papers.

  1. Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America

    Feb 16, 2026Yannis Karmim, Renato Pino, Hernan Contreras +6Cultural Bias in Language ModelsCultural Knowledge in Language Models

    ALMAnaCH · ALMAnaCH team, Inria Paris Center · Dept. of Computer Science, Universidad de Chile +8

  2. Robust Bias Evaluation with FilBBQ: A Filipino Bias Benchmark for Question-Answering Language Models

    Feb 16, 2026Lance Calvin Lim Gamboa, Yue Feng, Mark LeeSocial Bias in Language ModelsLanguage Model Bias Evaluation

    School of Computer Science, University of Birmingham · Department of Information Systems and Computer Science, Ateneo de Manila University

  3. A Scalable Entity-Based Framework for Auditing Bias in Large Language Models

    Jan 18, 2026Akram Elbouanani, Aboubacar Tuo, Adrian PopescuLLM AuditingPolitical Bias in Language Models

    Université Paris-Saclay, CEA, List, F-91120, Palaiseau, France

  4. Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages

    Oct 6, 2025Tarek Naous, Anagha Savit, Carlos Rafael Catalan +17Multilingual Language Model EvaluationCultural Bias in Language Models

    Georgia Institute of Technology · Samsung R&D Institute Philippines · Sungkyunkwan University +6

  5. What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models

    Oct 5, 2025Dustin Wright, Sarah Masud, Jared Moore +5LLM EvaluationCultural Bias in Language Models

    University of Copenhagen · Stanford University · University of Colorado Boulder +1

  6. One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning

    Sep 25, 2025Sualeha Farid, Jayden Lin, Zean Chen +2Multilingual Language Model EvaluationMoral Reasoning in Language Models

    University of Michigan, Ann Arbor, USA

  7. How K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices

    Sep 13, 2025Qing Xiao, Ruiwei Xiao, Hanqi Jane Li +4Generative AI in EducationGenerative AI Adoption

    Carnegie Mellon University, Pittsburgh, Pennsylvania, USA · University of California, San Diego, La Jolla, California, USA · University of Michigan, Ann Arbor, Michigan, USA

  8. Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs

    Aug 5, 2025Shintaro Sakai, Jisun An, Migyeong Kang +1Mental HealthCultural Bias in Language Models

    Indiana University Bloomington, USA · Sungkyunkwan University, Republic of Korea

  9. MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs

    Jun 11, 2024Vera Neplenbroek, Arianna Bisazza, Raquel FernándezSocial Bias in Language ModelsLanguage Model Bias Evaluation

    Institute for Logic, Language and Computation, University of Amsterdam · Center for Language and Cognition, University of Groningen