Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/pd90506/fairness_audit
Terminology
Sources
- Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models
- Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning
- Robustly Improving LLM Fairness in Realistic Settings via Interpretability
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow
- Evaluating and Mitigating Discrimination in Language Model Decisions
- Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection