让大模型推理过程更易被人类理解，便于纠错和协作。
Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning
- 用可验证的自包含步骤结构化推理链，提升可读性。
- 数学推理任务中性能与传统方法相当，但可解释性更强。
- 适合需要人机协作的高风险场景，如医疗、金融决策。
提升大语言模型（LLMs）的推理能力使其能应对更复杂的问题，而推理轨迹——通向解决方案的中间步骤——通过支持人工审查，为高风险应用开辟了新路径。然而，现有方法更关注模型性能，忽视人类可解释性，限制了有效的人机协作。本研究设计并评估了一种以人为中心的方法，将推理轨迹按自包含、可验证的步骤组织，使用户能独立评估和修正AI推理过程。该方法使用类似XML的标签编码推理内容与元数据，便于针对性反馈。在数学推理任务上的评估表明，该方法性能与标准链式思维（Chain-of-Thought）相当，同时显著提升可解释性。用户研究显示，感知有用性和易用性均有显著提升。本工作深化了对如何以用户为中心设计大模型输出的理解，更好满足高风险人工智能部署中的人类协作需求。
原文摘要 · Abstract (English)
Advancing reasoning capabilities allow large language models (LLMs) to tackle increasingly complex problems, while reasoning traces - intermediate steps toward solutions - open up high-stakes applications by enabling human inspection of AI decision-making. However, current approaches prioritize model performance over human interpretability, limiting effective human-AI collaboration. In this study, we design and evaluate a human-centered approach that structures reasoning traces based on self-contained, verifiable steps, enabling users to independently assess and correct AI reasoning. Our approach uses XML-like tags to encode reasoning content and metadata, facilitating targeted feedback. Evaluation on mathematical reasoning tasks shows our approach maintains equivalent performance to standard Chain-of-Thought reasoning while enhancing interpretability. User studies demonstrate significant improvements in perceived usefulness and ease of use. This work advances understanding of how user-centric design of LLM outputs can better serve human collaboration needs in high-stakes AI deployments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。