Metraipolis › archive › dc_57675be6d85d
"I Know Where to Look," But Does the LLM? Charting the Gaps Between Clinical Expert Needs and Unstructured Data Abstraction Tools — arXiv:2609.19318
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19318
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:00:26.699Z
- SHA-256 of the archived text
98bd8dc20fc05d57f36ed486a333e8fa49766a826cb02ac0d1afa71155e27431- Stable URL of this page
https://metraipolis.com/documento/dc_57675be6d85d
How to cite
"I Know Where to Look," But Does the LLM? Charting the Gaps Between Clinical Expert Needs and Unstructured Data Abstraction Tools — arXiv:2609.19318 — arXiv (en), https://arxiv.org/abs/2609.19318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57675be6d85d (Metraipolis archive dc_57675be6d85d, sha256 98bd8dc20fc05d57f36ed486a333e8fa49766a826cb02ac0d1afa71155e27431)
BibTeX
@misc{dc57675be6d85d,
title = {"I Know Where to Look," But Does the LLM? Charting the Gaps Between Clinical Expert Needs and Unstructured Data Abstraction Tools — arXiv:2609.19318},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19318},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57675be6d85d; sha256 98bd8dc20fc05d57f36ed486a333e8fa49766a826cb02ac0d1afa71155e27431},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Clinical data abstraction, the process of distilling structured information from patient records, plays a key role in advancing knowledge about diseases such as cancer. Information extraction (IE) with large language models (LLMs) could accelerate this process, but it is unclear whether current frameworks effectively support clinical researchers without AI expertise. To address this, we co-designed an interactive LLM-based abstraction system called Libretto with seven cancer research teams, then evaluated the system's ability to help them answer real-world research questions. We found that while clinicians knew where and how to annotate complex concepts in patient notes, in twelve of fourteen tasks they faced barriers to replicating those intuitions with LLMs. Contextual note reliability judgments, difficulties in steering vibe-coded prompts, and inflexible evaluation strategies necessitated fundamental changes to the IE workflow. Our results highlight open problems for HCI research to bridge the gaps between AI data work tools and clinical users' needs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Other Quantitative Biology (q-bio.OT). Pagina del lavoro: https://arxiv.org/abs/2609.19318 — 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 2026-10-10T03:28:23.619Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).