用递归分解构建可执行操作树，让手机本地高效回答复杂个人数据问题。
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
- 通过递归拆解问题生成可执行的操作树，统一处理结构化与非结构化数据。
- 在自建的PerQA基准上实现高准确率，支持从简单查询到分析型问题。
- 适合隐私敏感场景，所有数据留在设备端，无需上传云端。
在混合数据源（如文本和表格）上的问答已通过将内容全部转为自然语言并用语言模型编码取得进展。典型异构数据是个人数据：用户设备每日产生大量信息，包括日程、健身记录、购物历史、流媒体观看记录等。信息需求涵盖从简单查询到分析类问题。挑战在于以小体积实现便捷访问，确保所有个人数据保留在用户设备上。本文提出ReQAP方法，通过递归分解为给定问题创建可执行的操作树。操作符设计支持结构化与非结构化数据无缝集成，操作树执行可生成可追溯的答案。此外，我们发布了PerQA基准，包含基于人物设定的数据与问题，覆盖广泛真实的用户需求场景。
原文摘要 · Abstract (English)
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.
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。