cs.AIOct 30, 2026

RECITE: Revising Eligibility Criteria Incorporating Textual Evidence

Authors: Russell Ro, Reza Abbasi-Asl

Organizations: University of California, San Francisco · University of California, Berkeley

Abstract

Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific criteria should be broadened remain disconnected from trial design at scale. We introduce RECITE (Revising Eligibility Criteria Incorporating Textual Evidence), a framework for automated discovery, extraction, and implementation of evidence-based eligibility criteria revisions. RECITE uses protocol amendment documents from ClinicalTrials.gov to construct a dataset of 11,913 curated instances across 5,735 trials, each pairing original criteria with documentary evidence and target revisions. We benchmark fifteen LLM configurations under truncated-to-context-window and retrieval-augmented generation conditions, on a 3,116-instance sample under an LLM-as-judge protocol validated against ten domain experts (judge vs. human quadratic-weighted Cohen's κqw=0.694±0.096κ_{qw} = 0.694 \pm 0.096). The best open-weight model, Gemma 2 9B, achieves κqwκ_{qw}-aligned ordinal score 3.0±0.93.0 \pm 0.9 on a 0--4 scale (normalized 0.742) and the best closed-weight model, GPT-4o, reaches 3.0±0.83.0 \pm 0.8 (normalized 0.745). Using an agentic literature discovery system, we then identified 44 paper--trial matches across five publications providing trial-design and EC-modification evidence. Our findings suggest that existing clinical knowledge can be operationalized into actionable trial design recommendations.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

    Apr 3, 2026Yao Zhao, Zhiyue Zhang, Yanxun XuEvidence Selection

  2. TrialJev: Open-Weight Single Pass Eligibility Scoring for Patient Trial Screening

    Nov 6, 2026Omar Ibrahim, Grant Hamblin, Benjamin Haibe-KainsMedical LLMsEfficient Language Model Inference

  3. Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives

    Apr 6, 2026Ziyi Chen, Mengxian Lyu, Cheng Peng +1Medical LLMsClinical Language Model Evaluation