MVSS:多视图结构化调查生成的统一框架
MVSS: A Unified Framework for Multi-View Structured Survey Generation
AI总结:
本文提出MVSS框架,通过结构优先方法生成和对齐引用支撑的层级树、结构化比较表和调查文本,提升调查生成的结构组织和证据呈现质量。
摘要:
科学调查不仅需要总结大量文献,还需将其组织成清晰连贯的概念结构。然而,现有自动调查生成方法通常专注于线性文本生成,难以显式建模研究主题间的层次关系和结构化方法学比较,导致结构组织和证据呈现方面与专家撰写调查存在显著差距。为解决这一限制,我们提出了MVSS,一个多视图结构化调查生成框架,联合生成并对齐引用支撑的层级树、结构化比较表和调查文本。MVSS遵循结构优先范式:首先构建一个捕捉研究领域概念组织的树,然后在树结构约束下生成比较表,最后利用树和表作为联合结构约束指导大纲构建和调查文本生成。这种设计使结构、比较和叙述的多视图表示互补且对齐。此外,我们引入了一个专门的评估框架,系统地从多个维度评估生成的调查,包括结构性质量、比较完整性以及引用忠实度。通过在76个计算机科学主题上的大规模实验,我们证明MVSS在调查组织和证据支撑方面显著优于现有方法,并在多个评估指标上实现了与专家撰写调查相当的性能。
英文摘要:
Scientific surveys require not only summarizing large bodies of literature, but also organizing them into clear and coherent conceptual structures. However, existing automatic survey generation methods typically focus on linear text generation and struggle to explicitly model hierarchical relations among research topics and structured methodological comparisons, resulting in substantial gaps in structural organization and evidence presentation compared to expert-written surveys. To address this limitation, we propose MVSS, a multi-view structured survey generation framework that jointly generates and aligns citation-grounded hierarchical trees, structured comparison tables, and survey text. MVSS follows a structure-first paradigm: it first constructs a tree that captures the conceptual organization of a research domain, then generates comparison tables constrained by the tree structure, and finally uses both the tree and tables as joint structural constraints to guide outline construction and survey text generation. This design enables complementary and aligned multi-view representations across structure, comparison, and narrative. In addition, we introduce a dedicated evaluation framework that systematically assesses generated surveys from multiple dimensions, including structural quality, comparative completeness, and citation fidelity. Through large-scale experiments on 76 computer science topics, we demonstrate that MVSS significantly outperforms existing methods in survey organization and evidence grounding, and achieves performance comparable to expert-written surveys across multiple evaluation metrics.
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。