用离线模板生成实现快速精准的表格摘要，保护隐私且可复用。
FACTS: Table Summarization via Offline Template Generation with Agentic Workflows
- 离线生成含SQL与Jinja2模板的摘要框架，支持多表复用
- 在多个基准上超越基线，输出准确且响应快
- 仅传表结构给大模型，保障数据隐私适合实际应用
查询聚焦的表格摘要需基于用户查询生成自然语言摘要，帮助用户获取超出事实检索的洞察。现有方法存在明显缺陷：表格到文本模型需昂贵微调且难以处理复杂推理；基于提示的LLM方法受令牌限制影响效率并暴露敏感数据；先前的智能体流程常依赖分解、规划或人工模板，缺乏鲁棒性与可扩展性。为此，我们提出FACTS——一种通过离线模板生成实现快速、准确、符合隐私要求的表格摘要方法。FACTS生成包含SQL查询与Jinja2模板的离线模板，可渲染为自然语言摘要，并在共享相同模式的多个表格间复用。该方法通过可复用的离线模板实现快速摘要，利用可执行的SQL查询确保输出准确，并仅向LLM发送表结构以保障隐私。在广泛使用的基准上的评估表明，FACTS持续优于基线方法，确立了其在真实场景下查询聚焦表格摘要中的实用性。代码已开源：https://github.com/BorealisAI/FACTS。
原文摘要 · Abstract (English)
Query-focused table summarization requires generating natural language summaries of tabular data conditioned on a user query, enabling users to access insights beyond fact retrieval. Existing approaches face key limitations: table-to-text models require costly fine-tuning and struggle with complex reasoning, prompt-based LLM methods suffer from token-limit and efficiency issues while exposing sensitive data, and prior agentic pipelines often rely on decomposition, planning, or manual templates that lack robustness and scalability. To mitigate these issues, we introduce an agentic workflow, FACTS, a Fast, Accurate, and Privacy-Compliant Table Summarization approach via Offline Template Generation. FACTS produces offline templates, consisting of SQL queries and Jinja2 templates, which can be rendered into natural language summaries and are reusable across multiple tables sharing the same schema. It enables fast summarization through reusable offline templates, accurate outputs with executable SQL queries, and privacy compliance by sending only table schemas to LLMs. Evaluations on widely-used benchmarks show that FACTS consistently outperforms baseline methods, establishing it as a practical solution for real-world query-focused table summarization. Our code is available at https://github.com/BorealisAI/FACTS.
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。