Metraipolis › archive › dc_9923e6cd6ade

CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives — arXiv:2608.12779

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12779
License (as archived)
CC0-1.0
Archived
2026-10-19T04:18:08.284Z
SHA-256 of the archived text
5aee7fa3272d7b6f05a9fc9461bbd3700d6e6a70aa5e464b7916c1b69788a636
Stable URL of this page
https://metraipolis.com/documento/dc_9923e6cd6ade

How to cite

CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives — arXiv:2608.12779 — arXiv (en), https://arxiv.org/abs/2608.12779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9923e6cd6ade (Metraipolis archive dc_9923e6cd6ade, sha256 5aee7fa3272d7b6f05a9fc9461bbd3700d6e6a70aa5e464b7916c1b69788a636)
BibTeX
@misc{dc9923e6cd6ade,
  title = {CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives — arXiv:2608.12779},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12779},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9923e6cd6ade; sha256 5aee7fa3272d7b6f05a9fc9461bbd3700d6e6a70aa5e464b7916c1b69788a636},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.12779 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:13:06.702Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).