AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

LOOMSUM:Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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 generati

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T06:41:57.136Z. This is not the publication date.