CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
AI Digest - ArXiv AI
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does not guarantee that the CoT causally contributes to the final answer. Without this connection, outcome rewards may fail to reinforce high-quality reasoning. Existing causality metrics assess CoT causality by perturbing the CoT, such as deleting reasoning steps or injecting errors, and measuring changes
Source: ArXiv AI