Metraipolis › archive › dc_43aba64fcb46

LOOMSUM: Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization — arXiv:2609.00241

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00241
License (as archived): CC0-1.0
Archived: 2026-10-17T06:41:05.247Z
SHA-256 of the archived text: d96f45c020647ac288e2878a284078187891b62d8f1e0a73c09c99caab251563
Stable URL of this page: https://metraipolis.com/documento/dc_43aba64fcb46

How to cite

LOOMSUM: Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization — arXiv:2609.00241 — arXiv (en), https://arxiv.org/abs/2609.00241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43aba64fcb46 (Metraipolis archive dc_43aba64fcb46, sha256 d96f45c020647ac288e2878a284078187891b62d8f1e0a73c09c99caab251563)

BibTeX

@misc{dc43aba64fcb46,
  title = {LOOMSUM: Weaving Quantitative and Narrative Evidence for Faithful Long Text-Table Summarization — arXiv:2609.00241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43aba64fcb46; sha256 d96f45c020647ac288e2878a284078187891b62d8f1e0a73c09c99caab251563},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.00241 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:33:38.792Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).