作者位次 #3/3ICML 2026Poster· Social Aspects / Fairness
COFT: Counterfactual–Conformal Decoding for Fair Chain‑of‑Thought Reasoning in Large Language Models
Arya Fayyazi · Mehdi Kamal · Massoud Pedram
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Arya Fayyazi · Mehdi Kamal · Massoud Pedram
Seyedarmin Azizi · Erfan Baghaei Potraghloo · Souvik Kundu · Massoud Pedram
Large language models (LLMs) demonstrate strong performance on multi-step reasoning tasks by producing intermediate explanations, commonly referred to as chains of thought (CoTs). However, the generated rationales are typically verbose, consuming many additional tokens, and thus degrading through...