works on
counterfactual sensitivity 1language model training 1long chain-of-thought reasoning 1reinforcement learning 1token credit allocation 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.AI2026

Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning

Qiangqiang He, Zhongheng Wu, ZiJian Wang

The paper examines how uniformly assigning credit to all tokens during reinforcement learning for long chain‑of‑thought reasoning can be misleading, and introduces Counterfactual S…