ThreadSumm: 使用思维树进行嵌套讨论线的摘要
ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts
AI总结：
ThreadSumm通过多阶段LLM框架处理嵌套讨论线中的交错回复和引用，生成逻辑结构更清晰的摘要，同时提升观点覆盖和方面保留。
摘要：
对深度嵌套的讨论线进行摘要需要处理交错的回复、引用和重叠主题，这使标准LLM摘要器难以可靠捕捉。我们介绍了ThreadSumm，一种多阶段LLM框架，将讨论线摘要视为层次化推理问题，通过LLM提取话语方面和原子内容单元进行内容规划，然后应用句子排序构建具有多重观点的线意识序列。在这些可解释单元之上，ThreadSumm采用思维树搜索生成和评分多个段落候选，共同优化连贯性和覆盖度。通过多提案和迭代优化设计，我们展示了在生成逻辑结构更清晰的摘要方面优于现有基线的表现，同时在嵌套讨论中实现更高的方面保留和观点覆盖。
英文摘要：
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.
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。
