arXiv cs.CL· Jingxuan Wei, Song Tan, Xiaohan Liu, Chao Sang, Changwei Wang, Linzhuang Sun, Bihui Yu, Fuqiang Wang, Junnan Zhu·· 11 小时前AI 评分31
FindLink：从来源锚定前提学习评估科学关联
FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises
AI 导读
FindLink 是一个两阶段框架，用于基于来源的科学推理，通过前提锚定与结构化推理评估不同研究条件下发现之间的关联。团队同时发布 GI-TraceBench，包含 10,282 个胃肠肿瘤学问题，统一溯源问答、知识发现与假设评估。在 1,545 题固定证据测试集上，FindLink 将平衡家族宏平均分从 67.95 提升至 87.25。
正文 · 原文
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.
| Comments: | 28 pages, 10 figures. Dataset: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.02545 [cs.CL] |
| (or arXiv:2611.02545v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02545 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Song Tan [view email]
[v1]
Mon, 2 Nov 2026 05:15:38 UTC (1,448 KB)
来源：arXiv cs.CL · arxiv.org