CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives

2026-08-12

AI Summary

This study addresses the challenge of ambiguous symptom chronologies in clinical narratives caused by sparse temporal anchors. To resolve this, the authors propose CRAFT, a novel framework that, for the first time, reconstructs structured symptom trajectories within individual clinical reports. CRAFT integrates a large language model (LLM) generator with a constraint-driven verifier, leveraging an iterative feedback mechanism to refine the temporal ordering of symptom phases. The work introduces MedTempo, a new benchmark dataset for clinical temporal reasoning, and demonstrates that CRAFT consistently improves temporal accuracy across four distinct LLM backbones. Ablation studies further validate the contribution of each component to the framework’s overall performance.

Abstract

Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical narratives, however, rarely provide explicit temporal anchors. Current approaches to temporal information reasoning focus predominantly on pairwise relation classification across multi-visit and timestamp-rich records, leaving the reconstruction of structured symptom trajectories from individual anchor-sparse reports largely unaddressed. We propose CRAFT, an LLM framework that pairs a generator with a constraint-based verifier to iteratively produce and refine stage-wise symptom timelines through targeted feedback. We conduct evaluation on MedTempo, a new benchmark of 5,347 vaccine adverse-event narratives spanning three COVID-19 vaccine types, with expert-validated temporal stage annotations for 3,166 reports. Experiments across four LLM backbones demonstrate that CRAFT consistently improves temporal ordering accuracy, with ablation analysis isolating the contribution of generator and verifier components across model capability levels.

Problem

• temporal reasoning
• clinical narratives
• symptom trajectories
• temporal progression
• anchor-sparse reports

Innovation

• LLM-based iterative refinement
• temporal reasoning
• clinical narratives
• constraint-based verification
• symptom timeline reconstruction