Metraipolis › archive › dc_abc140d80f08

FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises — arXiv:2611.02545

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02545
License (as archived)
CC0-1.0
Archived
2026-11-03T18:23:42.397Z
SHA-256 of the archived text
401f8b24f5413376e144f9de83bda280a1e2a9f8d4317d3ec88843d86e519a12
Stable URL of this page
https://metraipolis.com/documento/dc_abc140d80f08

How to cite

FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises — arXiv:2611.02545 — arXiv (en), https://arxiv.org/abs/2611.02545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_abc140d80f08 (Metraipolis archive dc_abc140d80f08, sha256 401f8b24f5413376e144f9de83bda280a1e2a9f8d4317d3ec88843d86e519a12)
BibTeX
@misc{dcabc140d80f08,
  title = {FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises — arXiv:2611.02545},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02545},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_abc140d80f08; sha256 401f8b24f5413376e144f9de83bda280a1e2a9f8d4317d3ec88843d86e519a12},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scientific discovery from the literature requires assessing connections among findings obtained under different study conditions. Source attribution makes individual findings traceable, but does not determine what they jointly support. We introduce GI-TraceBench, a benchmark of 10,282 questions in gastrointestinal oncology that unifies provenance question answering, knowledge discovery, and hypothesis evaluation through shared Paper, Claim, and Evidence Span records. We further propose FindLink, a two-stage framework for provenance-grounded scientific reasoning. Premise Grounding constructs source-bound premises with explicit study context and support status. Structured Reasoning organizes these premises into support plans that represent both supported relations and unresolved conditions, then generates evidence-conditioned answers using deterministic compiler feedback. The compiler verifies structural and source-binding consistency, but does not assess scientific entailment. On the 1,545-question fixed-evidence test set, FindLink improves the balanced family macro score from 67.95 to 87.25 over direct supervised fine-tuning of the same backbone. A retrained variant without Structured Reasoning achieves slightly higher premise-identifier F1, but substantially lower relation and evidence-sufficiency F1. These results indicate that scientific reasoning requires not only identifying grounded premises, but also assessing what connections those premises support.

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/2611.02545 — 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 2026-11-03T18:10:07.972Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).