什么真的重要？检验多语言Co-T推理中的步骤和令牌级归因
What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning
AI总结：
本研究通过对比多语言Co-T推理中步骤和令牌级归因方法，揭示了归因分数的偏差及结构化提示对高资源语言准确性的影响，强调了多语言鲁棒性和解释透明性的挑战。
摘要：
本研究调查了多语言大语言模型中链式推理（CoT）推理背后的归因模式。尽管先前的工作展示了Co-T提示在提高任务性能中的作用，但存在关于生成推理链的忠实性和可解释性的担忧。为了评估这些属性在不同语言中的表现，我们应用了两种互补的归因方法——ContextCite用于步骤级归因和Inseq用于令牌级归因——对Qwen2.5 1.5B-Instruct模型进行测试，使用MGSM基准测试。我们的实验结果突显了几个关键发现：（1）归因分数过度强调最终推理步骤，特别是在错误生成中；（2）结构化的Co-T提示显著提高了准确性，主要在高资源拉丁字母语言中；（3）通过否定和干扰句子进行的受控扰动会降低模型的准确性和归因一致性。这些发现突显了Co-T提示的局限性，尤其是在多语言鲁棒性和解释透明性方面。
英文摘要：
This study investigates the attribution patterns underlying Chain-of-Thought (CoT) reasoning in multilingual LLMs. While prior works demonstrate the role of CoT prompting in improving task performance, there are concerns regarding the faithfulness and interpretability of the generated reasoning chains. To assess these properties across languages, we applied two complementary attribution methods--ContextCite for step-level attribution and Inseq for token-level attribution--to the Qwen2.5 1.5B-Instruct model using the MGSM benchmark. Our experimental results highlight key findings such as: (1) attribution scores excessively emphasize the final reasoning step, particularly in incorrect generations; (2) structured CoT prompting significantly improves accuracy primarily for high-resource Latin-script languages; and (3) controlled perturbations via negation and distractor sentences reduce model accuracy and attribution coherence. These findings highlight the limitations of CoT prompting, particularly in terms of multilingual robustness and interpretive transparency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
