arXiv · cs.AI · Xiao Yu, Justin Chih-Yao Chen, Zaid Khan, Hyunji Lee, Mohit Bansal · 12 小时前模型评分38
CRoS:在打乱顺序的思维链上施加因果奖励,提升准确率与推理忠实度
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
导读
研究提出思维链因果奖励方法CRoS(Causality Reward on Scrambled CoTs),通过打乱推理步骤顺序而不改动内容来评估思维链的因果作用,避免以往删除步骤或注入错误带来的信息变化干扰。
分类置信度
中 · 待人工复核
- 只有单一媒体来源,需要人工复核。
来源级别:媒体与个人
事件类型:研究发布
证据摘录
- “To address this problem, we propose CRoS (Causality Reward on Scrambled CoTs), a novel CoT causality metric that perturbs the order of reasoning steps without altering content, thereby preserving information within each step.”
来源:arXiv · cs.AI · arxiv.org