TimelyRAG：面向重叠演化文档中时间关键问答的语义-时间混合检索
TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents
浏览论文内容
中文总结 AI 辅助
针对法律等重叠演化文档中的时间关键问答，提出融合时间距离的检索框架TimelyRAG及基准TimelyQABench，实验显示nDCG@10提升达28.6%。
中文摘要 AI 辅助
尽管大型语言模型（LLMs）和检索增强生成（RAG）推动了开放域问答（QA）的发展，但当文档通过修订而演化时，它们仍然不可靠。现有的时间敏感检索方法仅处理不重叠演化环境，其中每次更新都是独立快照。然而，法律、政策和法规通常运行在重叠演化环境中，其中修订覆盖早期条款同时保留大部分内容，导致不同版本之间存在强烈的语义重叠。我们提出TimelyRAG，一个检索器无关的框架，将时间距离纳入排序，以使查询与版本适当的文档对齐。我们还引入了TimelyQABench，这是首个针对法规密集型领域且具有重叠演化挑战的基准。实验显示一致性的提升，nDCG@10最高提升+28.6%，凸显了时间推理对于演化文档上可靠QA的重要性。所有资源可在该https URL获取。
英文摘要
Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.
发表机构
- KAIST（韩国科学技术院）
- Korea University（韩国大学）
- University of Vermont（佛蒙特大学）
机构由 AI 辅助整理，请以论文原文为准。
