Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchCercetare AI

analiza aiqbench

The paper introduces GI-TraceBench, a 10,282-question benchmark in gastrointestinal oncology, and FindLink, a two-stage method for reasoning over source-grounded premises. The reported gain (macro score 67.95 to 87.25 over direct fine-tuning) is on one domain and one fixed test set, so it needs replication elsewhere. For AI readers, the useful signal is that identifying grounded evidence is not enough; the model must also judge how findings relate, and the paper's ablation suggests that step is where a model without structured reasoning falls short.
Sursă care acoperăarXiv

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

arXiv1 min de cititArticolul și perspectiva sunt în engleză.

arXiv:2611.02545v1 Announce Type: new Abstract: 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.

Citește articolul complet pe arXiv