Search papers, labs, and topics across Lattice.
This paper introduces CRAFT, an LLM-based framework designed to iteratively refine temporal reasoning in clinical narratives by generating and verifying stage-wise symptom timelines. By addressing the challenge of sparse temporal anchors in clinical reports, CRAFT enhances the accuracy of temporal ordering in symptom progression, which is crucial for effective disease monitoring and safety assessments. Evaluation on the MedTempo benchmark reveals that CRAFT significantly outperforms existing methods, demonstrating improved accuracy across various LLM backbones and highlighting the importance of its generator-verifier architecture.
CRAFT achieves unprecedented accuracy in reconstructing symptom timelines from sparse clinical narratives, transforming how we interpret temporal data in healthcare.
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.
