@inproceedings{ye-etal-2026-diagnosis,
title = "The Diagnosis Is Already in the Notes: A Channel-Wise Audit of Diagnostic Shortcuts in Clinical-Text Benchmarks",
author = "Ye, Haocun and
Jiang, Xinlong and
Hu, Yuanyuan and
Chen, Shubai and
Wu, Tingyu and
Zheng, Zhenkun and
Yi, Caijiao and
Zhang, Teng and
Wang, Liuxin and
Zhao, Tong and
Xu, Heping and
Dai, Weiwei and
Chen, Yiqiang",
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.381/",
pages = "8041--8060",
ISBN = "979-8-89176-462-0",
abstract = "Medical AI benchmarks routinely pair a diagnostic image with the same-visit clinical record, delete the recorded diagnosis, and treat what remains as auxiliary context. The recipe is reasonable. It is not. On 5904 ophthalmic visits across eight cohorts, a frozen text probe still recovers the disease label from the diagnosis-redacted record at 0.944 macro-AUROC, against 0.998 on the unredacted record; the most aggressive dictionary scrub closes less than one further percentage point. The diagnosis is already in the notes.\par It is not in one place. A clinical record is written during the diagnostic process, and its fingerprints persist across channels: narrative text alone reaches 0.978, and a view that erases every value and exposes only which fields were populated still reaches 0.854. We introduce CRAFT (Channel-wise Redaction And Floor Test), a portable audit protocol that renders each record into redacted and channel-isolated views and reports each channel{'}s label recoverability; rankings reproduce under Qwen3.5-9B. Before clinical-text or image-text fusion gains are read as cross-modal reasoning, the text branch{'}s channel-level shortcut floors must be reported alongside them. https://github.com/yhc98002-bit/The-Diagnosis-Is-Already-in-the-Notes"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-etal-2026-diagnosis">
<titleInfo>
<title>The Diagnosis Is Already in the Notes: A Channel-Wise Audit of Diagnostic Shortcuts in Clinical-Text Benchmarks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haocun</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinlong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanyuan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingyu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenkun</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caijiao</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liuxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heping</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqiang</namePart>
<namePart type="family">Chen</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>Medical AI benchmarks routinely pair a diagnostic image with the same-visit clinical record, delete the recorded diagnosis, and treat what remains as auxiliary context. The recipe is reasonable. It is not. On 5904 ophthalmic visits across eight cohorts, a frozen text probe still recovers the disease label from the diagnosis-redacted record at 0.944 macro-AUROC, against 0.998 on the unredacted record; the most aggressive dictionary scrub closes less than one further percentage point. The diagnosis is already in the notes.\par It is not in one place. A clinical record is written during the diagnostic process, and its fingerprints persist across channels: narrative text alone reaches 0.978, and a view that erases every value and exposes only which fields were populated still reaches 0.854. We introduce CRAFT (Channel-wise Redaction And Floor Test), a portable audit protocol that renders each record into redacted and channel-isolated views and reports each channel’s label recoverability; rankings reproduce under Qwen3.5-9B. Before clinical-text or image-text fusion gains are read as cross-modal reasoning, the text branch’s channel-level shortcut floors must be reported alongside them. https://github.com/yhc98002-bit/The-Diagnosis-Is-Already-in-the-Notes</abstract>
<identifier type="citekey">ye-etal-2026-diagnosis</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.381/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8041</start>
<end>8060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Diagnosis Is Already in the Notes: A Channel-Wise Audit of Diagnostic Shortcuts in Clinical-Text Benchmarks
%A Ye, Haocun
%A Jiang, Xinlong
%A Hu, Yuanyuan
%A Chen, Shubai
%A Wu, Tingyu
%A Zheng, Zhenkun
%A Yi, Caijiao
%A Zhang, Teng
%A Wang, Liuxin
%A Zhao, Tong
%A Xu, Heping
%A Dai, Weiwei
%A Chen, Yiqiang
%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 ye-etal-2026-diagnosis
%X Medical AI benchmarks routinely pair a diagnostic image with the same-visit clinical record, delete the recorded diagnosis, and treat what remains as auxiliary context. The recipe is reasonable. It is not. On 5904 ophthalmic visits across eight cohorts, a frozen text probe still recovers the disease label from the diagnosis-redacted record at 0.944 macro-AUROC, against 0.998 on the unredacted record; the most aggressive dictionary scrub closes less than one further percentage point. The diagnosis is already in the notes.\par It is not in one place. A clinical record is written during the diagnostic process, and its fingerprints persist across channels: narrative text alone reaches 0.978, and a view that erases every value and exposes only which fields were populated still reaches 0.854. We introduce CRAFT (Channel-wise Redaction And Floor Test), a portable audit protocol that renders each record into redacted and channel-isolated views and reports each channel’s label recoverability; rankings reproduce under Qwen3.5-9B. Before clinical-text or image-text fusion gains are read as cross-modal reasoning, the text branch’s channel-level shortcut floors must be reported alongside them. https://github.com/yhc98002-bit/The-Diagnosis-Is-Already-in-the-Notes
%U https://aclanthology.org/2026.findings-emnlp.381/
%P 8041-8060
Markdown (Informal)
[The Diagnosis Is Already in the Notes: A Channel-Wise Audit of Diagnostic Shortcuts in Clinical-Text Benchmarks](https://aclanthology.org/2026.findings-emnlp.381/) (Ye et al., Findings 2026)
ACL
- Haocun Ye, Xinlong Jiang, Yuanyuan Hu, Shubai Chen, Tingyu Wu, Zhenkun Zheng, Caijiao Yi, Teng Zhang, Liuxin Wang, Tong Zhao, Heping Xu, Weiwei Dai, and Yiqiang Chen. 2026. The Diagnosis Is Already in the Notes: A Channel-Wise Audit of Diagnostic Shortcuts in Clinical-Text Benchmarks. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 8041–8060, Budapest, Hungary. Association for Computational Linguistics.