用结构化思维链整合碎片证据，提升长问答的深度与准确
DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering
- 构建思维块链跟踪论点与证据关系
- 在多轮修正中发现新观点并完善引用
- 适合需要深度分析的科研与政策问答
检索-生成流水线常用于开放性问题的深度回答，但仅靠检索不足以支撑高质量答案：大模型需将杂乱碎片化的证据组织为全面、有据可依的回答。我们称此过程为证据合成。然而直接生成常导致证据利用不足、引证错位、信息泛化成浅层总结，暴露出检索与生成间的证据合成鸿沟。为此，我们提出 DeepWeaver 框架，通过维护思维块链（TBCs）——一种分组论点、关键信息、关键词和支撑证据的结构化表示——将噪声检索结果编织成完整回答。DeepWeaver 使用子级 TBC 检查残余证据，提交修订并发现新论点后再进行最终生成。我们在知识库和网页上的开放性问答任务上评估 DeepWeaver，引入高密度证据合成基准 LoQA。在多个 LLM 上，DeepWeaver 在 LoQA 上提升了内容充分性、引证准确性与细节保留度；在 DeepResearch Bench 上实现更深层次洞察与更高引证质量。结果表明，证据编织是弥合开放性问答中检索与生成差距的有效机制。代码已开源。
原文摘要 · Abstract (English)
Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLMs must organize noisy and fragmented evidence into comprehensive, well-cited answers. We refer to this process as evidence synthesis. However, direct generation often underuses evidence, misaligns citations, and collapses diverse information into shallow summaries, exposing an evidence synthesis gap between retrieval and generation. Thus, we propose DeepWeaver, a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence. DeepWeaver uses subordinate TBCs to inspect residual evidence, commit TBC revisions, and discover new claims before final generation. We evaluate DeepWeaver on open-ended QA over both knowledge bases and the web, and introduce LoQA, a high-density benchmark for evidence synthesis. Across multiple LLMs, DeepWeaver improves content sufficiency, citation grounding, and detail preservation on LoQA, while achieving deeper insights and higher citation quality on DeepResearch Bench. These results show that evidence weaving is an effective mechanism for bridging retrieval and generation in open-ended QA. Our code is available at https://github.com/KlozeWang/DeepWeaver.
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。