@inproceedings{feng-etal-2026-benchmarking,
title = "Benchmarking Large Language Models for Adaptive Information Acquisition and Diagnosis with Sequentially Revealed Inpatient Records",
author = "Feng, Huawei and
Shi, Dongsheng and
Wang, Linlin",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.474/",
pages = "9953--9964",
ISBN = "979-8-89176-462-0",
abstract = "While recent medical benchmarks for Large Language Models (LLMs) have begun to incorporate clinical temporality, they still overlook a key reality: clinical evidence is encountered incrementally, requiring repeated decisions between reviewing the next available record and committing to a prediction. To address this issue, we introduce [{\ensuremath{<}}https://github.com/hwfengcs/INA-Bench{\ensuremath{>}}] , a benchmark for Inpatient Note Acquisition that evaluates LLMs' ability to make acquire-or-predict decisions using sequentially revealed real-world Chinese inpatient records. In this benchmark, each case sequentially reveals up to three note blocks: an admission note, a first-course summary, and a daily-progress summary. After each block, the model under evaluation must either request the next block or predict one or more later documented follow-up actions (laboratory, imaging, pathology, or consultation). Surgery and discharge records are withheld for label construction and boundary checks only. is built from 8{,}986 de-identified inpatient records collected from two tertiary teaching hospitals, with patient-disjoint and temporal evaluation splits. Representative LLMs exhibit diverse acquire-or-predict behaviors. For example, DeepSeek-chat improves action micro-F1 by $+0.102$ and $+0.074$ on the patient-disjoint and temporal splits, respectively, while reading fewer note blocks, though the gains weaken under temporal drift."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2026-benchmarking">
<titleInfo>
<title>Benchmarking Large Language Models for Adaptive Information Acquisition and Diagnosis with Sequentially Revealed Inpatient Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huawei</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongsheng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>While recent medical benchmarks for Large Language Models (LLMs) have begun to incorporate clinical temporality, they still overlook a key reality: clinical evidence is encountered incrementally, requiring repeated decisions between reviewing the next available record and committing to a prediction. To address this issue, we introduce [\ensuremath<https://github.com/hwfengcs/INA-Bench\ensuremath>] , a benchmark for Inpatient Note Acquisition that evaluates LLMs’ ability to make acquire-or-predict decisions using sequentially revealed real-world Chinese inpatient records. In this benchmark, each case sequentially reveals up to three note blocks: an admission note, a first-course summary, and a daily-progress summary. After each block, the model under evaluation must either request the next block or predict one or more later documented follow-up actions (laboratory, imaging, pathology, or consultation). Surgery and discharge records are withheld for label construction and boundary checks only. is built from 8,986 de-identified inpatient records collected from two tertiary teaching hospitals, with patient-disjoint and temporal evaluation splits. Representative LLMs exhibit diverse acquire-or-predict behaviors. For example, DeepSeek-chat improves action micro-F1 by +0.102 and +0.074 on the patient-disjoint and temporal splits, respectively, while reading fewer note blocks, though the gains weaken under temporal drift.</abstract>
<identifier type="citekey">feng-etal-2026-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.474/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>9953</start>
<end>9964</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Large Language Models for Adaptive Information Acquisition and Diagnosis with Sequentially Revealed Inpatient Records
%A Feng, Huawei
%A Shi, Dongsheng
%A Wang, Linlin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F feng-etal-2026-benchmarking
%X While recent medical benchmarks for Large Language Models (LLMs) have begun to incorporate clinical temporality, they still overlook a key reality: clinical evidence is encountered incrementally, requiring repeated decisions between reviewing the next available record and committing to a prediction. To address this issue, we introduce [\ensuremath<https://github.com/hwfengcs/INA-Bench\ensuremath>] , a benchmark for Inpatient Note Acquisition that evaluates LLMs’ ability to make acquire-or-predict decisions using sequentially revealed real-world Chinese inpatient records. In this benchmark, each case sequentially reveals up to three note blocks: an admission note, a first-course summary, and a daily-progress summary. After each block, the model under evaluation must either request the next block or predict one or more later documented follow-up actions (laboratory, imaging, pathology, or consultation). Surgery and discharge records are withheld for label construction and boundary checks only. is built from 8,986 de-identified inpatient records collected from two tertiary teaching hospitals, with patient-disjoint and temporal evaluation splits. Representative LLMs exhibit diverse acquire-or-predict behaviors. For example, DeepSeek-chat improves action micro-F1 by +0.102 and +0.074 on the patient-disjoint and temporal splits, respectively, while reading fewer note blocks, though the gains weaken under temporal drift.
%U https://aclanthology.org/2026.findings-emnlp.474/
%P 9953-9964
Markdown (Informal)
[Benchmarking Large Language Models for Adaptive Information Acquisition and Diagnosis with Sequentially Revealed Inpatient Records](https://aclanthology.org/2026.findings-emnlp.474/) (Feng et al., Findings 2026)
ACL