ChatCite：具备人类工作流引导的用于比较性文献综述的LLM智能体
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary
AI总结：
针对现有LLM文献总结方法比较分析能力不足的问题，本研究提出模仿人类工作流、带反思增量机制的ChatCite智能体，还设计了G-Score评估指标，实验证明其多维度表现更优，生成内容可直接用于综述初稿。
摘要：
文献综述是研究过程中不可或缺的步骤，它既能帮助研究者理解研究问题与当前研究现状，还能对已有工作开展比较分析。然而，文献综述撰写难度高且耗时费力。此前基于大语言模型（LLM）的文献综述研究主要聚焦于文献检索、筛选、总结的完整流程，但在总结环节，简单的思维链（CoT）方法往往难以生成全面的比较性总结。本研究率先聚焦独立的文献总结环节，提出ChatCite——一种具备人类工作流引导的用于比较性文献总结的LLM智能体。该智能体模仿人类工作流，先从相关文献中提取关键要素，再通过反思增量机制生成总结。为更好地评估生成总结的质量，我们参考人类评估标准，设计了一种基于LLM的自动评估指标G-Score。实验中，ChatCite智能体在多个维度上的表现均优于其他模型，其生成的文献总结还可直接用于文献综述初稿的撰写。
英文摘要：
The literature review is an indispensable step in the research process. It provides the benefit of comprehending the research problem and understanding the current research situation while conducting a comparative analysis of prior works. However, literature summary is challenging and time consuming. The previous LLM-based studies on literature review mainly focused on the complete process, including literature retrieval, screening, and summarization. However, for the summarization step, simple CoT method often lacks the ability to provide extensive comparative summary. In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary. This agent, by mimicking the human workflow, first extracts key elements from relevant literature and then generates summaries using a Reflective Incremental Mechanism. In order to better evaluate the quality of the generated summaries, we devised a LLM-based automatic evaluation metric, G-Score, in refer to the human evaluation criteria. The ChatCite agent outperformed other models in various dimensions in the experiments. The literature summaries generated by ChatCite can also be directly used for drafting literature reviews.
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。
