Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More
Thinking in reasoning language models (RLMs) has been subject to debate on whether it resolves or amplifies bias. Prior works have shown competing conclusions in both directions. Using a within-model thinking-vs.-non-thinking ablation across QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, and Qwen3-32B on three high-stakes deci...
Deng Pan, Joe Germino, Yi-Hong Ma et al.
· 0 citations