Social Bias in Language Models

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 44% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 126

All topics

STEREODISCO: Discovering Stereotypicality in LLMs
Jul 30, 2026Farane Jalali Farahani, Corina Dima, Mojtaba Nayyeri +2Social Bias in Language Models Representation Geometry in Language Models
Institute for Artificial Intelligence, Stuttgart, Germany · Institute for Social Science, Stuttgart, Germany · University of Southampton, Southampton, United Kingdom
From Minds to Models: The Intersection of Psychology and LLM Behaviours
Jul 30, 2026Oliver Guidetti, Reza RyanSocial Bias in Language Models Implicit Bias
School of Psychology, Faculty of Science, Medicine and Health, University of Wollongong, Wollongong, NSW 2522, Australia. · School of Electrical Engineering, Computing and Mathematical Sciences, Faculty of Science and Engineering, Curtin University, Bentley, WA 6102, Australia.
Same Facts, Different Diagnosis: Measuring and Mitigating Narrative Anchoring in Clinical Language Models
Jul 29, 2026Prabhjot Singh, Pritam Deka, Vijay ChennareddySocial Bias in Language Models Clinical Reasoning
University of Texas at Austin Austin, Texas, USA · Queen’s University Belfast Belfast, United Kingdom · Middlesex University London, United Kingdom
Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Making
Jul 29, 2026Jiayuan Di, Haoyi Yang, Yufei Luo +2Social Bias in Language Models Cultural Bias in Language Models
East China University of Science and Technology · Mohamed bin Zayed University of Artificial Intelligence · Beijing University of Posts and Telecommunications +2
QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
Jul 23, 2026Emilio FerraraOpen-Ended Generation LLM Quantization
Thomas Lord Department of Computer Science University of Southern California
AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism
Jul 21, 2026Himel Ghosh, Ahmed Mosharafa, Georg GrohSocial Bias in Language Models Text Summarization
Technical University of Munich, Germany · Sapienza University of Rome, Italy
The Misclassification of Autistic Writing as AI-Generated
Jul 16, 2026Summer Chambers, Matthew C. KelleyAI-Generated Text Detection Social Bias in Language Models
George Mason University, Fairfax VA 22030, USA
Toward Localizing and Repairing Bias in Transformer Attention Heads
Jul 14, 2026Sigma JahanAttention Head Analysis Social Bias in Language Models
Dalhousie University, Canada
When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation
Jul 8, 2026Yahan Zheng, John Guerrerio, Soroush Vosoughi +1Debiased ML Social Bias in Language Models
Dartmouth College · Oakland University
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
Jul 8, 2026Weicheng Ma, John Guerrerio, Soroush VosoughiMultilingual Language Model Evaluation Social Bias in Language Models
College of Computing, Georgia Institute of Technology · Computer Science Department, Dartmouth College
LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering
Jul 7, 2026Huan Wu, Ali Emami, Muhammad Furquan Hassan +5Language Model Steering Social Bias in Language Models
1York University · 2Vector Institute · Connected Minds +6
RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs
Jul 6, 2026Damian Hodel, Jevin West, Aylin CaliskanLLM Evaluation Social Bias in Language Models
University of Washington, Seattle, USA
Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG
Jun 30, 2026Naihao Deng, Yilun Zhu, Joan Nwatu +2Language Model Steering Social Bias in Language Models
University of Michigan
Can LLMs Hire Fairly? Racial Bias in Resume Screening
Jun 27, 2026Zhenyu Gao, Wenxi Jiang, Yutong YanGender Bias in Language Models Social Bias in Language Models
Department of Finance, CUHK Business School, The Chinese University of Hong Kong
To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias
Jun 23, 2026Federico Marcuzzi, Xuefei Ning, Roy Schwartz +1Pairwise Comparison LLM Auditing
INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria · Tsinghua University, China · The Hebrew University of Jerusalem, Israel +1
UnBias-Plus: Detect, Explain, and Rewrite Bias
Jun 22, 2026Ahmed Y. Radwan, Ahmed ElKady, Sindhuja Chaduvula +3Explainable Artificial Intelligence Social Bias in Language Models
Vector Institute for Artificial Intelligence, Toronto, Canada · Independent Researcher
Same question, different history: language, national identity, and credit in large language models
Jun 22, 2026William Guey, Pierrick Bougault, Wei Zhang +2Social Bias in Language Models Cultural Bias in Language Models
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
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
The Almost Intelligent Revolution: Options for Scaling Up Deliberation and Empowering People with AI
Jun 18, 2026Serge SharoffSocial Bias in Language Models Computational Argumentation
School of Languages, Cultures and Societies, University of Leeds, UK
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Jun 17, 2026Naihao Deng, Yiming Feng, Chimaobi Okite +4LLM Grounding LLM Alignment
University of Michigan · University of Cambridge · University of Aberdeen
Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement
Jun 16, 2026Ramaravind Kommiya Mothilal, Terry Jingchen Zhang, Raiyan Ahmed +3LLM-as-a-Judge Social Bias in Language Models
University of Toronto · Vector Institute · EuroSafeAI +1
P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs
Jun 15, 2026Rafael Ferreira, Inês Vieira, Inês Calvo +6Multilingual Language Model Evaluation Social Bias in Language Models
NOVA University of Lisbon, Portugal · NOVA LINCS
MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions
Jun 15, 2026Noor Islam S. Mohammad, Tamim SheikhLLM Safety Benchmarks LLM Auditing
Department of Computer Science, Informatics Institute, Istanbul Technical University, ˙Istanbul, Türkiye · Department of Computer Science and Engineering, Jashore University of Science and Technology, Bangladesh.
A Mechanistic Understanding of Pronoun Fidelity in LLMs
Jun 15, 2026Katharina Trinley, Jesujoba O. Alabi, Dietrich Klakow +1Social Bias in Language Models LLM Interpretability
Saarland University, Germany · Heidelberg Institute for Theoretical Studies, Germany
Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models
Jun 13, 2026Kieron Seven Jun Wei Lee, Muhammad Reza Qorib, Andrew Ivan Soegeng +1Multilingual Language Models Social Bias in Language Models
National University of Singapore · Carnegie Mellon University · SAP
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
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Jun 9, 2026Naihao Deng, Yilun Zhu, Naichen Shi +2LLM Alignment Social Bias in Language Models
University of Michigan · Northwestern University
Neutrality Bites: Gender Representation in AI-Generated Animal Stories
Jun 6, 2026Imani Finkley, Yuanxi Li, Melanie WalshGender Bias in Language Models Social Bias in Language Models
University of Washington, Seattle, Washington, USA
What Does Debiasing Really Remove? A Geometric Study of PCA-Based Gender Debiasing in Word Embeddings
Jun 6, 2026Alexey Kresin, Tchifou M. Dieffi, Tomer CaspiNeural Representation Geometry Word Embeddings
Department of Computer Science, Hood College, Frederick, MD, United States · Department of Mathematics, Ben-Gurion University of the Negev, Be'er Sheva, Israel
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

Jul 30, 2026, cs.AIJ/K move · Enter open · S save

STEREODISCO: Discovering Stereotypicality in LLMs

Farane Jalali Farahani, Corina Dima, Mojtaba Nayyeri, Raphael H. Heiberger+1

Institute for Artificial Intelligence, Stuttgart, Germany · Institute for Social Science, Stuttgart, Germany · University of Southampton, Southampton, United Kingdom

Social Bias in Language Models Representation Geometry in Language Models

Open paper AskPDF arXiv

LLMs encode, convey, and perpetuate stereotypes. Prior computational research focuses on a small set of semantic axes investigated in social psychology, and operates on word embeddings produced by language models, leaving open which other semantic axes carry stereotypical associations in LLMs and how LLMs internally represent such axes. We introduce STEREODISCO, a framework that adapts the semantic differential method (Osgood et al., 1957) to the systematic study of stereotypes in LLM internal representations. STEREODISCO constructs approx. 2,000 candidate semantic axes from WordNet antonym synsets, recovers each as a geometric axis in the LLM's activation space via probing, and identifies stereotypical axes via a statistical test over concept projections. As a case study, we apply STEREODISCO to social group stereotypes with LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT. We find that the two LLMs agree with each other on social group ratings more than with humans, suggesting that LLM-encoded stereotype content diverges from that documented in social psychology. We also discover stereotypical axes not investigated in prior work -- including humble vs. proud, narrow-minded vs. broad-minded, and cowardly vs. brave, which human annotators independently confirm.

Momentum

Related topics

Latest papers 126