Safety
Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions
arXiv:2609.40124v1 Announce Type: new Abstract: Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that re
arXiv:2609.40124v1 Announce Type: new Abstract: Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that reduce stereotypical thinking and prejudiced responses in humans. We propose Debias It Yourself (DIY), a cognitively grounded framework that translates five such interventions into debiasing procedures for large language models and delivers them through three established paradigms: Show (in-context examples), Train (instruction tuning), and Revise (guided self-revision). Across three models, five bias benchmarks, eleven debiasing baselines, and three reasoning benchmarks, Train+Revise and Revise alone attain the top two average ranks, lead the bias-reasoning tradeoff (mean bias as low as 2% at 90% reasoning accuracy), and reduce bias on unseen dimensions by up to 14.8%. Our code and data are publicly available.
Related
- Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs
- Multi-Persona Thinking for Bias Mitigation in Large Language Models
- Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation
- Bias in Large Language Models: Origin, Evaluation, and Mitigation
Source: arXiv cs.CL | 2026-10-01