arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.18446cs.CLcs.AI
收藏

ReportLogic: 评估深度研究报告的逻辑质量

ReportLogic: Evaluating Logical Quality in Deep Research Reports

Leiden Institute of Advanced Computer Science, Leiden University(莱顿先进计算机科学研究所,莱顿大学);Ant Group(蚂蚁集团);CISPA Helmholtz Center for Information Security(信息安全霍普夫中心)

Jujia Zhao, Zhaoxin Huan, Zihan Wang, Xiaolu Zhang, Jun Zhou, Suzan Verberne, Zhaochun Ren

AI总结:

提出ReportLogic基准,通过可审计性视角量化报告逻辑质量,包含宏观逻辑、阐述逻辑和结构逻辑三层评估,并训练开源LogicJudge进行可扩展评估。

摘要:

用户越来越依赖大型语言模型(LLMs)进行深度研究,利用它们将多样化的来源综合成结构化的报告,以支持理解和行动。在这种情况下,此类报告的实际可靠性取决于逻辑质量:报告的主张和论点是否得到明确支持,并且可以作为下游使用的基础,而不仅仅是表面上流畅或信息丰富。然而,当前的评估框架在很大程度上忽略了这一要求。为了弥补这一差距,我们引入了ReportLogic,这是一个通过以读者为中心的可审计性视角量化报告级逻辑质量的基准。具体来说,ReportLogic采用分层分类法,评估读者是否能够(1)追踪具有统一分析弧线的主题报告结构(宏观逻辑),(2)在必要的上下文中理解进展(阐述逻辑),以及(3)通过明确的主张-支持关系验证结论(结构逻辑)。基于这一分类法,我们构建了一个带有人工注释的评分指南数据集,并训练了一个开源的LogicJudge用于可扩展评估。我们进一步通过对抗性攻击评估判断器的鲁棒性,表明现成的LLM判断器经常受到表面线索(例如冗长)的影响,并且推理模式可能掩盖断裂的支持关系。总体而言,我们的结果为构建更鲁棒的逻辑评估器以及提高LLM生成报告的逻辑可靠性提供了可操作的指导。

英文摘要:

Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action. In this context, the practical reliability of such reports hinges on logical quality: whether the report's claims and arguments are explicitly supported and can be trusted as a basis for downstream use, rather than merely appearing fluent or informative. However, current evaluation frameworks largely overlook this requirement. To bridge this gap, we introduce ReportLogic, a benchmark that quantifies report-level logical quality through a reader-centric lens of auditability. Specifically, ReportLogic adopts a hierarchical taxonomy that evaluates whether readers can (1) trace an on-topic report structure with a unified analytical arc (Macro-Logic), (2) understand the progression with necessary context (Expositional-Logic), and (3) verify conclusions via explicit claim--support (Structural-Logic). Based on this taxonomy, we construct a human-annotated rubric-guided dataset and train an open-source LogicJudge for scalable evaluation. We further evaluate judge robustness via adversarial attacks, showing that off-the-shelf LLM judges are frequently influenced by superficial cues (e.g., verbosity), and reasoning modes can mask broken support relations. Overall, our results provide actionable guidance for building more robust logic evaluators and improving the logical reliability of LLM-generated reports.

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。

↑