Research
ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts
arXiv:2604.17648v1 Announce Type: new Abstract: Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers strug
arXiv:2604.17648v1 Announce Type: new Abstract: 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.
Related
- Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
- Calibrating Model-Based Evaluation Metrics for Summarization
- Testimole-Conversational: A 30-Billion-Word Italian Discussion Board Corpus (1996-2024) for Language Modeling and Sociolinguistic Research
- What makes an entity salient in discourse?
Source: arXiv cs.CL | 2026-04-21