DeepWeaver：弥合开放域问答中的证据合成鸿沟
DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering
浏览论文内容
中文总结 AI 辅助
该研究针对开放域问答中检索与生成间的证据合成鸿沟，提出DeepWeaver框架，通过Thought Block Chains编织证据，在LoQA和DeepResearch Bench基准上提升了问答的内容、引用及见解质量。
中文摘要 AI 辅助
检索后生成的流程常用于为开放域问题生成深度研究答案，但仅靠检索是不够的：大型语言模型（LLMs）必须将嘈杂且碎片化的证据组织成全面、有规范引用的答案，我们将这一过程称为证据合成。然而，直接生成往往无法充分利用证据、引用错位，还会将多样化信息压缩为浅显的摘要，暴露出检索与生成之间的证据合成鸿沟。因此，我们提出DeepWeaver，这是一种新型框架，通过维护Thought Block Chains（TBCs，一种将主张、重要信息、关键词及支撑证据分组的结构化表示），将嘈杂的检索证据编织成全面的答案。DeepWeaver使用从属TBC检查剩余证据、提交TBC修订并在最终生成前发现新主张。我们在知识库和网络上的开放域问答任务中对DeepWeaver进行评估，并引入LoQA——一个用于证据合成的高密度基准。在多个LLMs上，DeepWeaver在LoQA上提升了内容充分性、引用依据性和细节保留度，同时在DeepResearch Bench上实现了更深入的见解和更高的引用质量。这些结果表明，证据编织是弥合开放域问答中检索与生成之间差距的有效机制。我们的代码可在此URL获取。
英文摘要
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.
发表机构
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
