发表机构
HKUST(GZ)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对表格到报告生成中探索偏差问题，提出ComInsight方法，通过原子洞察的组合与结构化图组织，生成可验证的复合结论，在三个基准上优于现有基线。
AI 中文摘要
表格到报告生成是指从关系表格中自动生成文章级分析报告的任务，是自动化数据科学和决策支持的关键能力。其核心挑战在于系统地发现跨表格、属性和分析视角的可验证复合洞察，并将其组织成连贯、完整且可追溯的证据链。现有方法主要依赖于顺序的、反应式的数据代理或直接的大语言模型（LLM）生成。它们存在探索偏差：早期的局部观察约束了后续行动，导致模型过早地聚焦于局部分析，而遗漏跨表格或跨维度的证据。我们提出ComInsight，将洞察发现重新表述为原子证据的组合。我们首先将原子洞察定义为符合预定义分析模式的最小可执行分析单元，并从数据库模式和内容中枚举所有有效的原子洞察。然后，这些原子被组织成一个多关系洞察图，其中节点表示经过验证的数据事实，边编码逻辑、时间或层次关系。最后，一组组合操作符系统地将原子节点融合成更高阶的复合结论。每个复合输出都附带可执行的SQL和细粒度的来源信息，确保完全可验证性。在InsightBench、DDR-Bench和T2R-Bench三个基准上，ComInsight在事实正确性、新颖性和结构完整性方面始终优于强基线。我们相信ComInsight为表格到报告生成提供了一条可靠、高效且可解释的路径。
英文摘要
Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attributes, and analytical perspectives, and organizing them into coherent, complete, and traceable evidence chains. Existing methods primarily rely on sequential, reactive data agents or direct Large Language Model(LLM) generation. They suffer from exploration bias: early local observations constrain subsequent actions, causing models to focus prematurely on local analyzes and miss cross-table or cross-dimensional evidence. We propose ComInsight, which reformulates insight discovery as the composition of atomic evidences. We first define an atomic insight as the smallest executable analytical unit conforming to a predefined analysis pattern and enumerate all valid atomic insights from database schema and content. These atoms are then organized into a multi-relational insight graph, where nodes represent verified data facts and edges encode logical, temporal, or hierarchical relations. Finally, a set of composition operators systematically fuses atomic nodes into higher-order composite conclusions. Every composite output is accompanied by executable SQL and fine-grained provenance, ensuring full verifiability. Across three benchmarks InsightBench, DDR-Bench, and T2R-Bench, ComInsight consistently outperforms strong baselines in factual correctness, novelty, and structural completeness. We believe ComInsight offers a reliable, efficient, and explainable path toward table-to-report generation.
