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

arXiv: https://arxiv.org/abs/2608.12779 · HTML: https://mlsanity.com/paper/2608.12779/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 5 of its 37 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 5 of 5)

- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (2023)
- [Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction](https://mlsanity.com/paper/2405.10288/) (2024)
- [Prompting Large Language Models for Clinical Temporal Relation Extraction](https://mlsanity.com/paper/2412.04512/) (2024)
- [Transformer-Based Temporal Information Extraction and Application: A Review](https://mlsanity.com/paper/2504.07470/) (2025)

## Abstract (arXiv)

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.