Demographic Bias in Language Models

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 80

All topics

Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders
Jul 23, 2026Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino +3LLM Interpretability Cultural Bias in Language Models
Universidad Autónoma de Occidente Cali, Colombia · Universidad Autónoma de Occidente GobLab-UAI Cali, Colombia
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
Jul 22, 2026Haran Shani-Narkiss, Michael Fire, Oren TsurLLM Evaluation LLM Alignment
University College London, London, England. · Ben-Gurion University of the Negev, Be’er Sheba, Israel.
The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students
Jul 13, 2026Alexis Popovici, Andrei Ionascu, Adrian-Marius DumitranLanguage Model Safety Evaluation AI in Education
Universitatea din Bucuresti, Bucharest, Romania
Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues
Jun 30, 2026Mohammadamin Shafiei, Shuyue Stella Li, Yulia TsvetkovLanguage Model Safety Evaluation Language Model Bias Evaluation
University of Milan · University of Washington
Demographic Metadata as Construct-Irrelevant Noise in DistilBERT-Based Automated Essay Scoring
Jun 19, 2026Teik Peng Ch'ng, Hui Na ChuaAutomated Essay Scoring Demographic Bias in Language Models
Sunway University School of Computing and Artificial Intelligence, Faculty of Engineering and Technology, Sunway University, Malaysia
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
Jun 18, 2026Shaghayegh Kolli, Timo Cavelius, Nafiseh Nikeghbal +2Social Bias in Language Models Multimodal Large Language Models
Technical University of Munich · Munich Center for Machine Learning · Princeton Center for Information and Technology Policy
AgentFairBench: Do LLM Agents Discriminate When They Act?
Jun 15, 2026Triveni Morla, Rohith Reddy Bellibaltu, Manpreet Singh +1Algorithmic Fairness LLM Agent Evaluation
Florida International University, Miami, FL 33199 USA · Boston University, Boston, MA 02215 USA · Department of Computer Science and Engineering, Indian Institute of Technology Patna, Patna, Bihar, India
A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions
Jun 12, 2026Kehinde Temitayo SoetanLanguage Model Bias Evaluation Demographic Bias in Language Models
Department of Medical Humanities and Social Sciences The Ohio State University
Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research
Jun 10, 2026Andrés Abeliuk, Cinthia Sanchez Macias, Valentina Alarcón +2Gender Bias in Language Models Social Bias in Language Models
Department of Computer Science University of Chile Center for Artificial Intelligence (CENIA) Santiago, Chile · Center for Artificial Intelligence (CENIA) Santiago, Chile · Institute of Sociology Pontificia Universidad Católica de Chile Santiago, Chile
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
Jun 10, 2026Shun Shao, Zheng Zhao, Anna Korhonen +2Debiased ML Algorithmic Fairness
University of Cambridge · University of Edinburgh · University of Groningen +1
Pareto-Guided Teacher Alignment for Fair Personalized Text Generation
Jun 8, 2026Tunazzina IslamLanguage Model Bias Evaluation Multi-Objective Language Model Alignment
Department of Computer Science Purdue University, West Lafayette Indiana 47907, USA
The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search
Jun 4, 2026Hana Samad, Trung Lam, Christoph Mügge-Durum +1LLM Auditing Social Bias in Language Models
Responsible AI Lab · Chief AI Officer and Head of the Responsible AI Lab, National Fair Housing Alliance, Washington DC, USA
From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation
Jun 4, 2026Paloma Piot, Javier ParaparLLM-Assisted Annotation Hate Speech Detection
Information Retrieval Lab CITIC Research Centre Universidade da Coruña
Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails
Jun 4, 2026Marco Antonio Stranisci, A Pranav, Rossana Damiano +2LLM Guardrails Training Data Curation
University of Turin, Italy · Trustworthy AI Lab, University of Hamburg, Germany · IT University of Copenhagen, Denmark
Large Language Models in K-12 Education: Alignment with State Curriculum Standards and Student Personas
Jun 3, 2026Lisa Korver, Tomo Lazovich, Sherief RedaLLM Evaluation AI in Education
Department of Computer Engineering · Brown University · Providence, RI 02906 +1
The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction
Jun 1, 2026Mirko Lai, Alessandra Urbinati, Simona Frenda +2Annotator Disagreement Conformal Prediction
Heriot-Watt University, Edinburgh, Scotland · aequa-tech, Torino, Italy · Laboratory for the Modeling of Biological and Socio-technical Systems, Northeastern University, Boston, MA, USA +2
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
Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation
May 27, 2026Neemias da Silva, Matt Ratto, Myriam Delgado +3Multimodal Large Language Models Language Model Bias Evaluation
University of Toronto, Toronto, Canada · Universidade Tecnologica Federal do Parana, Curitiba, Brazil
Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
May 27, 2026Annabella Sánchez-Guzmán, Lukas Eberhard, Denis Helic +1LLM Auditing LLM Prompting
Escuela Superior Polit´ecnica del Litoral · Graz University of Technology · Complexity Science Hub
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
May 27, 2026Shadmehr Zaregarizi, Khashayar YavariReward Shaping Algorithmic Fairness
Politecnico di Torino Turin, Italy
Insidious by Design: Implications of Large Language Model algorithmic bias for the Global South
May 26, 2026Sioux McKenna, Nompilo TshumaGender Bias in Language Models Cultural Bias in Language Models
Rhodes University, Makhanda, South Africa · Stellenbosch University, Stellenbosch, South Africa
When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening
May 22, 2026Jianfeng Zhu, Megan Korhummel, Ruoming Jin +1Medical Diagnosis Mental Health
Departments of Computer Science1 and Psychological Science2 Kent State University Kent, OH USA
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
Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
May 12, 2026Jagdish Tripathy, Marcus BuckmannLLM Auditing Implicit Bias
Bank of England
Causal Bias Detection in Generative Artificial Intelligence
May 12, 2026Drago PleckoAlgorithmic Fairness Language Model Bias Evaluation
Department of Statistics & Data Science UCLA
Explanation Fairness in Large Language Models: An Empirical Analysis of Disparities in How LLMs Justify Decisions Across Demographic Groups
May 9, 2026Gautam VeldandaLLM Auditing Algorithmic Fairness
Independent Researcher
The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models
May 6, 2026Alif Al Hasan, Sumon BiswasLLM Safety Benchmarks Language Model Safety Evaluation
Department of Computer and Data Sciences Case Western Reserve University Cleveland, OH, USA
Measuring and Mitigating Bias in Code Generated by Large Language Models
May 5, 2026Yuxi Chen, Yutian Tang, Timothy StorerAlgorithmic Bias Language Model Bias Evaluation
School of Computing Science, University of Glasgow, United Kingdom.
Auditing demographic bias in AI-based emergency police dispatch: a cross-lingual evaluation of eleven large language models
May 2, 2026William Guey, Wei Zhang, Pierrick Bougault +4Multilingual Language Model Evaluation LLM Auditing
Department of Industrial Engineering, Tsinghua University, Beijing, China · School of Social Sciences, Tsinghua University, Beijing, China · Department of Industrial Engineering, Federal University of Rio de Janeiro, Brazil
Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior
Apr 30, 2026Ali Aghazadeh Ardebili, Massimo StellaSocial Bias in Language Models Language Model Bias Evaluation
CogNosco Lab, University of Trento, Department of Psychology and Cognitive Science, Trento, Italy

Jul 23, 2026, cs.CLJ/K move · Enter open · S save

Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders

Pablo Santiago Potes Velasco, María del Mar García Matabanchoy, Óscar Julián Pérez Ladino, Jhoan Stevan Mosquera Ortiz+2

Universidad Autónoma de Occidente Cali, Colombia · Universidad Autónoma de Occidente GobLab-UAI Cali, Colombia

LLM Interpretability Cultural Bias in Language Models Linguistic Bias in Language Models Demographic Bias in Language Models Language Model Probing

Open paper AskPDF arXiv

Large language models may infer demographic attributes from subtle linguistic cues even when those attributes are not explicitly stated. This pilot study examines whether Qwen2.5-7B-Instruct internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts. We use Natural Language Autoencoders (NLA) to verbalize residual-stream activations from layer 20 across four positional quartiles per prompt. Our dataset contains 30 prompts arranged as 15 matched Spanish-English pairs, spanning explicit Colombian cues, implicit Colombian cues, and neutral controls. We report descriptive rates and qualitative evidence rather than statistically powered effects, focusing on whether latent nationality or stereotype representations appear before they are verbalized in the model output. This work connects activation-level interpretability with bias evaluation for underrepresented Spanish varieties.

Momentum

Related topics

Latest papers 80