phenomenon · first seen 10 Oct 2026
social bias in large language models
Also: speaker bias, stereotype bias audit, social bias evaluation, gender bias in language models, social bias in language models
Systematic unfair associations related to identity groups exhibited by language model outputs.
Mentions per week
PapersCodeDiscussion
Rank 197 on 31 Oct 2026 · 9 mentions in 28 days · 9 independent groups · papers · first seen 3 weeks ago · acceleration -0.83
Earliest sources
- Social Bias in Chinese Large Language Models under Social Media ExpressionsPapers · 10 Oct 2026 · Mo Zhou
- Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)Papers · 13 Oct 2026 · Weitong Li, Donglin Song, Junkai Lin, Xi Xuan
- Analyzing Occupational Gender Bias across the LLM Training LifecyclePapers · 16 Oct 2026 · Manthan Gadhia, Alexander Hoyle, Karolina Stańczak
- Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language ModelsPapers · 20 Oct 2026 · Koshiro Saito, Daisuke Oba, Danushka Bollegala, Naoaki Okazaki
- Guilt by Association: Semantic Leakage Drives Associative Gender BiasPapers · 20 Oct 2026 · Hazel Chen, Peter West, Hila Gonen
- Investigating the Impact of Learner Errors on Social Bias in Large Language ModelsPapers · 21 Oct 2026 · Federico Marcuzzi, Martin Christoph, Iryna Gurevych, Alla Rozovskaya
Latest sources
- WarBias: A Bilingual LLM Benchmark of Stereotypes About Internally Displaced People and VeteransPapers · 8 Nov 2026 · Viktoriia Makovska, Tetiana Zakharchenko, Oleksandra Ostafiichuk
- The Male Abstraction Bias in Internet Culture and Large Language ModelsPapers · 3 Nov 2026 · Douglas Guilbeault, Bhargav Srinivasa Desikan
- From Language to Country to Valence: A Multilingual Audit of Stereotype Bias Across LLMsPapers · 2 Nov 2026 · Zihao Sun
- When the Top Answer Decides: Gender Bias in Decision ModelsPapers · 29 Oct 2026 · Yeb Havinga
- From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers BelievePapers · 28 Oct 2026 · Nouar AlDahoul, Yasir Zaki
- Gender Associations in LLM-Mediated ADHD Self-DiagnosisPapers · 24 Oct 2026 · Matilde Elene Hansen, Ross Deans Kristensen-McLachlan
- Investigating the Impact of Learner Errors on Social Bias in Large Language ModelsPapers · 21 Oct 2026 · Federico Marcuzzi, Martin Christoph, Iryna Gurevych, Alla Rozovskaya
- Guilt by Association: Semantic Leakage Drives Associative Gender BiasPapers · 20 Oct 2026 · Hazel Chen, Peter West, Hila Gonen
- Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language ModelsPapers · 20 Oct 2026 · Koshiro Saito, Daisuke Oba, Danushka Bollegala, Naoaki Okazaki
- Analyzing Occupational Gender Bias across the LLM Training LifecyclePapers · 16 Oct 2026 · Manthan Gadhia, Alexander Hoyle, Karolina Stańczak
- Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)Papers · 13 Oct 2026 · Weitong Li, Donglin Song, Junkai Lin, Xi Xuan
- Social Bias in Chinese Large Language Models under Social Media ExpressionsPapers · 10 Oct 2026 · Mo Zhou