COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models 事件

COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models arXiv:2605.30641v1 Announce Type: new Abstract: Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language mo