用检索代替生成，精准定位会议中话题出现的时间点。
Topic-to-Timestamp Alignment by Constrained Evidence Selection
- 通过候选时间片段筛选替代直接生成时间码，提升定位准确性。
- 在420个查询上，召回率从31.9%提升至50.0%，误差降低。
- 适合需要高精度时间定位的会议搜索场景，尤其关注结果可解析性。
用户记得讨论内容但记不清时间时，会议档案难以搜索。本文研究话题到时间戳对齐问题：给定自然语言话题和带时间戳的会议转录文本，目标是返回该话题被讨论的时间。标准RAG框架虽可检索相关片段，但仍需语言模型生成时间戳，易产生无依据或无效时间码。为此，本文将时间预测重构为受限的时间候选选择：系统检索带时间戳的文本片段，模型从中选出最符合话题的候选，而非生成时间码。在200份市政会议转录的420个话题-时间查询上，该方法将Recall@5从31.9%提升至50.0%，平均绝对误差从837.0秒降至761.0秒（使用Mistral-7B-Instruct），可解析输出数量从373增至419/420。结果表明，长文本中的时间定位高度依赖检索质量与输出设计，而不仅取决于语言模型选择。
原文摘要 · Abstract (English)
Meeting archives are difficult to search when users remember what was discussed but not when. We study topic-to-timestamp alignment: given a natural-language topic and a timestamped meeting transcript, the goal is to return the time at which the topic is discussed. A standard RAG setup can retrieve relevant transcript excerpts, but still asks the language model to generate a timestamp, which can produce unsupported or invalid timecodes. We therefore recast timestamp prediction as constrained temporal candidate selection: the system retrieves timestamped transcript chunks, and the model selects the candidate that best grounds the topic instead of generating a timecode. On 420 topic-timestamp queries from 200 municipal meeting transcripts, this increases Recall@5 from 31.9% to 50.0%, reduces MAE from 837.0 seconds to 761.0 seconds with Mistral-7B-Instruct, and increases the number of parseable outputs from 373 to 419 of 420 queries. The results suggest that temporal grounding in long transcripts depends strongly on retrieval quality and output design, not only on the choice of the language model.
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。