Metraipolis › archive › dc_6898241feca1
The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation — arXiv:2610.19387
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19387
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:23:47.571Z
- SHA-256 of the archived text
697c60eb9ef46a7afe2ff020e376db97d1777f43afcb5f57913772457881b708- Stable URL of this page
https://metraipolis.com/documento/dc_6898241feca1
How to cite
The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation — arXiv:2610.19387 — arXiv (en), https://arxiv.org/abs/2610.19387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6898241feca1 (Metraipolis archive dc_6898241feca1, sha256 697c60eb9ef46a7afe2ff020e376db97d1777f43afcb5f57913772457881b708)
BibTeX
@misc{dc6898241feca1,
title = {The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation — arXiv:2610.19387},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19387},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6898241feca1; sha256 697c60eb9ef46a7afe2ff020e376db97d1777f43afcb5f57913772457881b708},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scores clearly, make diverse data available, or evaluate models directly on the task. This paper proposes PROPALIGN, a multiple-summary-based approach for propositional salience score estimation, and releases PROPALIGNBANK, an accompanying dataset for the method with 138K alignments of over 35K propositions. We compare several approaches to salient proposition extraction in English across a broad range of spoken and written genres, and demonstrate that naively asking models for judgments leads to inconsistencies. By contrast, graded, summary-based metrics are more stable. We further observe that while single models perform worse than humans, an ensemble of models incorporating linguistic features approaches manual annotation quality ceilings. In addition, analyses of the model outputs suggest insights into how models can extract salient information with and without the use of summaries. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.19387 — 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 2026-10-15T19:36:18.188Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).