Metraipolis › archive › dc_7f482af30905

Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum — arXiv:2609.25028

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25028
License (as archived)
CC0-1.0
Archived
2026-10-08T14:34:17.238Z
SHA-256 of the archived text
5551b687119412def4d2406a186cdd9558ef6a7dc046cc6ccdbc933384f8a732
Stable URL of this page
https://metraipolis.com/documento/dc_7f482af30905

How to cite

Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum — arXiv:2609.25028 — arXiv (en), https://arxiv.org/abs/2609.25028 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f482af30905 (Metraipolis archive dc_7f482af30905, sha256 5551b687119412def4d2406a186cdd9558ef6a7dc046cc6ccdbc933384f8a732)
BibTeX
@misc{dc7f482af30905,
  title = {Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum — arXiv:2609.25028},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25028},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f482af30905; sha256 5551b687119412def4d2406a186cdd9558ef6a7dc046cc6ccdbc933384f8a732},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25028. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

QMSum provides no scorer, making query-focused meeting summarization results difficult to compare. We rescore or generate 15 systems under one implementation. Through a common inference port, a released 406M Fusion-in-Decoder specialist loses 6.30 ROUGE-1 when moved from capped long input to 2,000-word retrieved spans. Fine-tuning it on this span regime recovers the loss. On test it scores 36.33 ROUGE-1 versus 35.41 for our 1.2B system; the meeting-cluster 95% interval for the difference is [-0.27, +2.22], so QMSum does not statistically separate them. The smaller system uses about one-third as many total parameters and less than half the peak inference memory. Within the fixed 1.2B base, span-regime fine-tuning adds 5.29 [+4.02, +6.56], while replacing the first 4,500 transcript words with 2,000 retrieved words adds 1.55 on test and 0.29 on validation. Separately, under one concise prompt and reference-overlap scorer, a released 406M specialist exceeds five proprietary hosted models by at least 6.2 ROUGE-1, but output length and absent human or factuality evaluation limit this ordering. Conclusions are limited to QMSum and automatic metrics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.25028 — 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 2026-10-08T13:46:15.646Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).