Metraipolis › archive › dc_3fc50252fdc6

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering — arXiv:2608.27467

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27467
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:44.962Z
SHA-256 of the archived text
6cb95cc744b1af0168e015e3e594f1be6e82b66d228444c189580042f8e380cf
Stable URL of this page
https://metraipolis.com/documento/dc_3fc50252fdc6

How to cite

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering — arXiv:2608.27467 — arXiv (en), https://arxiv.org/abs/2608.27467 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fc50252fdc6 (Metraipolis archive dc_3fc50252fdc6, sha256 6cb95cc744b1af0168e015e3e594f1be6e82b66d228444c189580042f8e380cf)
BibTeX
@misc{dc3fc50252fdc6,
  title = {UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering — arXiv:2608.27467},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27467},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fc50252fdc6; sha256 6cb95cc744b1af0168e015e3e594f1be6e82b66d228444c189580042f8e380cf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27467. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participated in Subtasks 2 (evidence identification), 3 (answer generation), and 4 (answer-evidence alignment). For Subtasks 2 and 3, we propose an answer-first pipeline in which the model generates candidate answers citing specific note sentences before classifying the full evidence set, exploiting the asymmetry between judging relevance in the abstract versus relative to a generated answer. For Subtask 4, we apply self-consistency voting over five independent model calls, retaining links by vote threshold. Our pipeline ranked third on evidence identification (Strict Micro F1 62.90), ninth on answer generation (Overall 31.90), and fifth on answer-evidence alignment (F1 79.81). A post-hoc linguistic analysis of 45 stylistic features reveals that model outputs remain 3.2 Flesch-Kincaid grade levels harder to read than clinician-authored references despite matching their word and sentence counts, suggesting readability warrants explicit optimization in clinical NLP systems. Code and prompts are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.27467 — 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 2026-10-17T10:33:42.441Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).