Problem
Research questions and friction points this paper is trying to address.
Long Text-Table Summarization
Analytical Faithfulness
Quantitative Facts
LOOMSUM:Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization
🤖 AI Summary
为解决长文档和表格忠实总结难题，提出LOOMSUM框架，提取证据并链接表格与叙述分析，提升总结的分析准确性。
📝 Abstract
Long documents often distribute important information across extensive narrative passages and multiple tables, making faithful summarization particularly challenging. Existing methods may generate individually supported quantitative facts and analytical statements yet associate them incorrectly, producing quantitatively plausible yet analytically unfaithful summaries. In this work, we propose LOOMSUM, a training-free framework that extracts source-grounded atomic evidence, explicitly links table-derived facts with supporting narrative analyses, and plans the discourse structure before generation. We also introduce Table-Grounded Faithfulness (TGF), a claim-level metric that separately evaluates Numeric Grounding, Analysis Support, and Relation Consistency. Experiments on the text--table summarization benchmarks FINDSum and USTT show that LOOMSUM improves analytical faithfulness while maintaining strong summarization quality. Human evaluation finds positive component-level associations with the corresponding human judgments. Our Relation Consistency metric further shows stronger agreement with human relation judgments than generic factuality metrics, indicating that explicit cross-modal linking helps reduce errors in which supported quantities are paired with incorrect narrative interpretations. Together, these findings show that faithful long text--table summarization requires not only grounding individual facts, but also preserving the relations between them.
Innovation
Methods, ideas, or system contributions that make the work stand out.
LOOMSUM
Table-Grounded Faithfulness
cross-modal linking
analytical faithfulness
🔎 Similar Papers
No similar papers found.
