Metraipolis › archive › dc_afcfc068010f

MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue — arXiv:2611.08433

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08433
License (as archived)
CC0-1.0
Archived
2026-11-06T14:42:57.147Z
SHA-256 of the archived text
72e70117fbc05161d906ac26f6b74b3b539fb63afff753492c53897f57bfe5a3
Stable URL of this page
https://metraipolis.com/documento/dc_afcfc068010f

How to cite

MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue — arXiv:2611.08433 — arXiv (en), https://arxiv.org/abs/2611.08433 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afcfc068010f (Metraipolis archive dc_afcfc068010f, sha256 72e70117fbc05161d906ac26f6b74b3b539fb63afff753492c53897f57bfe5a3)
BibTeX
@misc{dcafcfc068010f,
  title = {MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue — arXiv:2611.08433},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08433},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afcfc068010f; sha256 72e70117fbc05161d906ac26f6b74b3b539fb63afff753492c53897f57bfe5a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08433. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based medical assistants that follow a patient across visits need a memory that keeps the patient's clinical state correct as it changes. We examine the errors of five memory systems on longitudinal medical dialogue and find three recurring causes: the retrieved evidence gives an outdated state, includes another person's health facts, or lacks a safety fact the answer depends on. We present MedGraph, a graph memory built for these three cases. Construction extracts dated facts from each session, attributes each fact to the person it describes, and links medication, diagnosis, and measurement records into chains that keep earlier states. Retrieval ranks the patient's chains as units, reads each chain at the time the question asks about, and adds the original dialogue text; a patient profile lists every recorded safety fact with every question. On MedMemoryBench, MedGraph has the highest overall accuracy with both a GPT and a Qwen backbone, 10.5 and 10.4 points above the strongest of five baselines, with efficient memory construction and answering in the GPT setting.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.08433 — 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 2026-11-06T14:18:42.703Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).