用思维树框架总结嵌套讨论，更好捕捉多观点和复杂结构。
ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts
- 将讨论线分解为语义单元与议题，分阶段构建可解释的摘要
- 在多个候选摘要中搜索优化，提升逻辑连贯性与议题覆盖度
- 适合需要精准还原多视角争议的对话分析任务
深度嵌套的讨论线总结需处理交错回复、引用及重叠话题，现有大模型摘要器难以可靠捕捉。我们提出 ThreadSumm，一种多阶段大模型框架，将线程摘要视为对显式议题与内容单元表示的层次化推理问题。方法首先通过大模型提取论述议题与原子内容单元进行内容规划，再通过句子排序构建感知线程的序列，呈现多重观点而非单一线性脉络。在此可解释单元基础上，ThreadSumm采用思维树搜索生成并评估多个段落候选，联合优化一致性与覆盖度。该多提案与迭代精炼设计显著优于现有基线，在逻辑结构化摘要生成上表现更优，同时在嵌套讨论中实现更高议题保留率与观点覆盖率。
原文摘要 · Abstract (English)
Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers struggle to capture reliably. We introduce ThreadSumm, a multi-stage LLM framework that treats thread summarization as a hierarchical reasoning problem over explicit aspect and content unit representations. Our method first performs content planning via LLM-based extraction of discourse aspects and Atomic Content Units, then applies sentence ordering to construct thread-aware sequences that surface multiple viewpoints rather than a single linear strand. On top of these interpretable units, ThreadSumm employs a Tree of Thoughts search that generates and scores multiple paragraph candidates, jointly optimizing coherence and coverage within a unified search space. With this multi-proposal and iterative refinement design, we show improved performance in generating logically structured summaries compared to existing baselines, while achieving higher aspect retention and opinion coverage in nested discussions.
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。