用图结构增强大模型长文档摘要能力，提升内容准确性和一致性。
StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs
- 通过句子图结构注入局部上下文与重要性信号，改进提示工程。
- 在ArXiv数据集上事实一致性与摘要质量分别提升19.2%和8.0%。
- 无需训练，适用于零样本提取式摘要，适合关注内容忠实度的研究者。
大语言模型在零样本摘要任务中表现强劲，但在建模长文档结构和识别关键信息方面仍存在困难。本文提出StrucSum，一种无需训练的提示框架，通过句子级图结构增强大模型推理能力。该方法采用三种策略：邻域感知提示（NAP）捕捉局部上下文，中心性感知提示（CAP）估计句子重要性，中心性引导掩码（CGM）实现高效输入压缩。在ArXiv、PubMed和Multi-News数据集上的实验表明，StrucSum显著优于无监督基线和原始提示方法。尤其在ArXiv上，FactCC与SummaC指标分别提升19.2%和8.0%，显示摘要与原文内容更强的一致性。消融实验表明，多策略组合未带来明显增益；因此，基于图结构的语义提示为零样本提取式摘要提供了有前景且尚未充分探索的方向。代码已开源。
原文摘要 · Abstract (English)
Large language models (LLMs) have shown strong performance in zero-shot summarization, but often struggle to model document structure and identify salient information in long texts. In this work, we introduce StrucSum, a training-free prompting framework that enhances LLM reasoning through sentence-level graph structures. StrucSum injects structural signals into prompts via three targeted strategies: Neighbor-Aware Prompting (NAP) for local context, Centrality-Aware Prompting (CAP) for importance estimation, and Centrality-Guided Masking (CGM) for efficient input reduction. Experiments on ArXiv, PubMed, and Multi-News demonstrate that StrucSum consistently improves both summary quality and factual consistency over unsupervised baselines and vanilla prompting. In particular, on ArXiv, it increases FactCC and SummaC by 19.2\% and 8.0\% points, demonstrating stronger alignment between summaries and source content. The ablation study shows that the combination of multiple strategies does not yield clear performance gains; therefore, structure-aware prompting with graph-based information represents a promising and underexplored direction for the advancement of zero-shot extractive summarization with LLMs. Our source code is publicly available.
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。