STRUM-LLM：带归因与结构化的对比式摘要
STRUM-LLM: Attributed and Structured Contrastive Summarization
AI总结：
本文提出 STRUM-LLM，一种无需人工标注即可生成带归因、结构化对比摘要的方法，帮助用户在 A/B 选项中识别关键差异，并通过蒸馏模型实现 100 倍吞吐量提升。
摘要：
用户常常在两个选项（A 与 B）之间难以做出决策，因为这通常需要在多个网页上进行耗时的研究。我们提出 STRUM-LLM，通过生成带归因、结构化且有用的对比式摘要来应对这一挑战，突出两个选项之间的关键差异。STRUM-LLM 识别有用的对比：即两个选项差异显著且最可能影响用户决策的具体属性。我们的技术领域无关，不需要任何人工标注数据或固定属性列表作为监督。STRUM-LLM 将所有抽取内容归因回输入来源，并提供文本证据，且对其可处理的输入来源长度没有限制。STRUM-LLM Distilled 的吞吐量比性能相当的模型高 100 倍，同时规模小 10 倍。在本文中，我们为我们的方法提供了广泛的评估，并为我们当前已部署的系统规划了未来方向。
英文摘要：
Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresses this challenge by generating attributed, structured, and helpful contrastive summaries that highlight key differences between the two options. STRUM-LLM identifies helpful contrast: the specific attributes along which the two options differ significantly and which are most likely to influence the user's decision. Our technique is domain-agnostic, and does not require any human-labeled data or fixed attribute list as supervision. STRUM-LLM attributes all extractions back to the input sources along with textual evidence, and it does not have a limit on the length of input sources that it can process. STRUM-LLM Distilled has 100x more throughput than the models with comparable performance while being 10x smaller. In this paper, we provide extensive evaluations for our method and lay out future directions for our currently deployed system.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
