RESEARCH · RESEARCH · #1496
FD-SCoPE: verifiable, feedback-driven LLM framework for clinician queries over trial evidence tables
The paper (arXiv:2610.02576v1) introduces FD-SCoPE, a language-model framework that answers clinician-style questions over systematic-review evidence tables by exposing the query, selected trials, and derivation rule for each answer and learning from expert corrections. On an oncology table of 159 immune checkpoint inhibitor trial records it completed 140 clinician-style tasks (alternatives 90.7–97.9%), retrieved 99.3% of relevant records for derived attributes with 89.8% PPV, achieved derived-value F1 77.7% (vs. 64.8–73.4% for four baselines), and raised F1 on 1,201 unseen questions from 77.9% to 84.9% after simulated corrections.
KEY POINTS
- The paper (arXiv:2610.02576v1) introduces FD-SCoPE, a language-model framework that answers clinician-style questions over systematic-review evidence tables by exposing the query, selected trials, and derivation rule for each answer and learning from expert corrections.
- On an oncology table of 159 immune checkpoint inhibitor trial records it completed 140 clinician-style tasks (alternatives 90.7–97.9%), retrieved 99.3% of relevant records for derived attributes with 89.8% PPV, achieved derived-value F1 77.7% (vs.
- 64.8–73.4% for four baselines), and raised F1 on 1,201 unseen questions from 77.9% to 84.9% after simulated corrections.
WHY IT MATTERS
FD-SCoPE demonstrates that coupling LMs with executable queries, verifiable derivations, and expert feedback can produce auditable, higher-accuracy answers from trial evidence tables relevant to clinicians.