评估逐步推理轨迹：一项综述
Evaluating Step-by-step Reasoning Traces: A Survey
AI总结：
本文综述了LLM逐步推理轨迹的评估方法，提出涵盖事实性、有效性、连贯性和实用性的分类体系，并回顾相关数据集、评估器及研究发现，为未来研究提供方向。
摘要：
逐步推理被广泛用于增强大型语言模型（LLMs）在复杂问题上的推理能力。评估推理轨迹的质量对于理解和改进LLM推理至关重要。然而，现有的评估实践高度不一致，导致评估器设计和基准开发方面的进展碎片化。为弥补这一空白，本综述对逐步推理评估进行了全面概述，提出了一个包含四个顶层类别（事实性、有效性、连贯性和实用性）的评估标准分类体系。基于该分类体系，我们回顾了不同的数据集、评估器实现以及近期研究发现，从而为未来研究指明了有前景的方向。
英文摘要：
Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However, existing evaluation practices are highly inconsistent, resulting in fragmented progress across evaluator design and benchmark development. To address this gap, this survey provides a comprehensive overview of step-by-step reasoning evaluation, proposing a taxonomy of evaluation criteria with four top-level categories (factuality, validity, coherence, and utility). Based on the taxonomy, we review different datasets, evaluator implementations, and recent findings, leading to promising directions for future research.
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。
