Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models

arXiv:2610.02576v1 Announce Type: new Abstract: Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug's target class or a harmonised endpoint. Here we introduce FD-SCoPE, a language-model framework that answers both kinds of question, exposes the query, the selected trials and the derivation rule behind every answer, and learns from expert corrections. On an oncology evidence table of 159 immune checkpoint inhibitor trial records, FD-SCoPE completed all 140 clinician-style tasks (alternatives, 90.7-97.9%). For questions needing derived attributes it retrieved 99.3% of relevant trial records at a positive predictive value of 89.8% and outperformed four alternative approaches (derived-value F1 77.7% versus 64.8-73.4%). Corrections on 299 questions, simulated from reference answers, raised F1 on 1,201 unseen questions from 77.9% to 84.9%. Language models coupled with executable queries, verified programs and expert feedback can give clinicians auditable access to trial evidence.

Related

• Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
• Can Language Models Analyze Data? Evaluating Large Language Models for Question Answering over Datasets
• S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA

Source: arXiv cs.AI | 2026-10-05