Metraipolis › archive › dc_48cfdab3e66b

Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes — arXiv:2610.01324

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01324
License (as archived)
CC0-1.0
Archived
2026-10-06T13:55:27.157Z
SHA-256 of the archived text
eda47a768907a70e2daf5e9b5b9266520c1be3fbf5474f035e720eab87ed29d7
Stable URL of this page
https://metraipolis.com/documento/dc_48cfdab3e66b

How to cite

Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes — arXiv:2610.01324 — arXiv (en), https://arxiv.org/abs/2610.01324 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48cfdab3e66b (Metraipolis archive dc_48cfdab3e66b, sha256 eda47a768907a70e2daf5e9b5b9266520c1be3fbf5474f035e720eab87ed29d7)
BibTeX
@misc{dc48cfdab3e66b,
  title = {Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes — arXiv:2610.01324},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01324},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48cfdab3e66b; sha256 eda47a768907a70e2daf5e9b5b9266520c1be3fbf5474f035e720eab87ed29d7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01324. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Patient-specific clinical question answering requires locating the right evidence within long, heterogeneous longitudinal clinical records in which relevant facts may be scattered across encounters, repeated in copied-forward notes, or expressed using different clinical terminology. We evaluated whether biomedical reranking can improve evidence selection and downstream answer quality in a locally deployed retrieval-augmented generation pipeline for longitudinal clinical notes. The pipeline combines PubMedBERT dense retrieval, BM25 lexical retrieval, weighted reciprocal-rank fusion, and MedCPT cross-encoder reranking. Across 1,000 open- and closed-ended question-answer pairs from a cohort of 200 bariatric surgery patients, reranking increased exact source-chunk retrieval within the top 10 items, Hit@10 from 46.6% to 60.6% and mean reciprocal rank from 0.2371 to 0.3252. With Qwen3-8B generation, local judge-assessed answer correctness increased from 44.8% to 48.6%. These results show that biomedical reranking can improve the placement of relevant clinical evidence within a limited context window, although gains in retrieval do not translate proportionally into gains in answer correctness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Emerging Technologies (cs.ET).
Pagina del lavoro: https://arxiv.org/abs/2610.01324 — 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 2026-10-06T12:15:34.709Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).