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

• URL: http://arxiv.org/abs/2608.12779v1
• Date: Thu, 13 Aug 2026 03:37:11 GMT
• Title: CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
• Abstract summary: CRAFT is a framework that produces and refines stage-wise symptom timelines through targeted feedback.<n>We evaluate MedTempo, a new benchmark of 5,347 vaccine adverse-event narratives spanning three COVID-19 vaccine types.
• Score: 5.378407274546433
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication [2.981889575213664]
  We present a UID-preserving framework that links each narrative event occurrence to its source span.<n>We also present GAVEL, an LLM judge that compares two UID-aligned timelines against the narrative and structured record.
  arXiv  Detail & Related papers  (2026-09-11T17:01:10Z)
• STRIVE: Multi-Agent Structured Temporal Reasoning with Integrated Verification for Longitudinal Radiology Report Generation [16.079764988150306]
  STRIVE decomposes clinical reasoning into specialized Diagnosis, Attribute, and Temporal Change Agents.<n>On Longitudinal-MIMIC, STRIVE attains the best clinical efficacy among recent methods.
  arXiv  Detail & Related papers  (2026-08-25T08:43:15Z)
• How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning? [49.14050864978079]
  We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning, and structured localization guidance.<n>The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints.
  arXiv  Detail & Related papers  (2026-08-13T14:35:20Z)
• From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction [61.12883122613684]
  This Review focuses on intervention-aware disease trajectory modeling in clinical AI--methods estimating patient-specific longitudinal disease evolution and assessing trajectory changes under alternative treatments.<n>We organize the field around six linked components: three decision tasks (factual forecasting, counterfactual estimation, policy evaluation) and three data-generating mechanisms (disease evolution, treatment assignment, observation process) that determine identifiability.<n>We present the first unified framework bridging forecasting, counterfactual trajectories, and policy evaluation across discrete/continuous time, explicitly addressing treatment assignment, time-varying confounding, and observation bias.
  arXiv  Detail & Related papers  (2026-05-16T10:45:26Z)
• Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment [4.42383617731229]
  We introduce a retrieval-augmented multimodal alignment framework to improve the temporal precision of absolute clinical timelines extracted from text.<n>Our approach formulates timeline reconstruction as a graph-based multistep process.
  arXiv  Detail & Related papers  (2026-05-14T17:55:27Z)
• MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction [8.92515305370631]
  We propose a framework to align predictive modeling with clinical logic.<n>We introduce Plateau-Gaussian Soft Labeling (PSL) to reformulating binary classification into continuous multi-horizon regression.<n>Our framework demonstrates superior efficacy and robust generalization in capturing risks from text-intensive, irregular clinical time series.
  arXiv  Detail & Related papers  (2026-04-02T07:45:52Z)
• Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling [3.6611037112655818]
  We developed a time-series corpus of case reports involving glucagon-like peptide 1 receptor agonists.<n>We evaluated automated LLM timeline extraction against gold-standard timelines annotated by clinical domain experts.<n>The best-performing LLM produced high event coverage, reliable temporal sequencing across symptoms, diagnoses, treatments, laboratory tests, and outcomes.
  arXiv  Detail & Related papers  (2026-03-12T20:45:06Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• MIMIC-SR-ICD11: A Dataset for Narrative-Based Diagnosis [14.505360834752866]
  We introduce MIMIC-SR-ICD11, a large English diagnostic dataset built from EHR discharge notes and aligned to WHO ICD-11 terminology.<n>We present LL-Rank, a likelihood-based re-ranking framework that computes a length-normalized joint likelihood of each label given the clinical report context.
  arXiv  Detail & Related papers  (2025-11-07T18:55:22Z)
• LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP [2.2615384250361004]
  This study introduces a novel LLM-augmented clinical NLP pipeline that employs domain-adapted large language models for symptom extraction, contextual reasoning, and correlation from free-text reports.<n> Evaluations on MIMIC-III and CARDIO-NLP datasets demonstrate improved performance in precision, recall, F1-score, and AUROC, with high clinical relevance.
  arXiv  Detail & Related papers  (2025-07-15T07:32:16Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [50.56875995511431]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• Deep State-Space Generative Model For Correlated Time-to-Event Predictions [54.3637600983898]
  We propose a deep latent state-space generative model to capture the interactions among different types of correlated clinical events. Our method also uncovers meaningful insights about the latent correlations among mortality and different types of organ failures.
  arXiv  Detail & Related papers  (2024-07-28T02:42:36Z)
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response [58.0291320452122]
  This paper aims at a unified deep learning approach to predict patient prognosis and therapy response. We formalize the prognosis modeling as a multi-modal asynchronous time series classification task. Our predictive model could further stratify low-risk and high-risk patients in terms of long-term survival.
  arXiv  Detail & Related papers  (2020-10-08T15:30:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.