Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification

Justin Xu; Alistair Johnson; Thomas Lin; David Eyre; Rodolfo Quispe

Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification

Justin Xu, Alistair Johnson, Thomas Lin, David Eyre, Rodolfo Quispe

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

De-identification systems prioritize recall to protect privacy, but excessive over-tagging reduces data utility. We propose an agentic refiner that reviews high-recall annotations using lightweight tools (validation functions, adaptive context retrieval, persistent to-do state, and modular review skills) to improve precision while minimizing recall loss. Experiments across three multilingual datasets show that the agent achieves significant improvements to binary precision. To support fine-grained analysis, we further introduce a synthetic error dataset of common and systemic failure modes, on which the agent corrects 99% of injected errors in the medical datasets. Our results suggest that agent-based refinement provides a flexible and effective mechanism for improving de-identification precision as a modular extension to existing high-recall systems.

Anthology ID:: 2026.bionlp-1.11
Volume:: BioNLP 2026
Month:: July
Year:: 2026
Address:: San Diego, California
Editors:: Dina Demner-Fushman, Sophia Ananiadou, Kirk Roberts, Junichi Tsujii
Venues:: BioNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 115–127
Language:
URL:: https://aclanthology.org/2026.bionlp-1.11/
DOI:
Bibkey:
Cite (ACL):: Justin Xu, Alistair Johnson, Thomas Lin, David Eyre, and Rodolfo Quispe. 2026. Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification. In BioNLP 2026, pages 115–127, San Diego, California. Association for Computational Linguistics.
Cite (Informal):: Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification (Xu et al., BioNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.bionlp-1.11.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{xu-etal-2026-post,
    title = "Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification",
    author = "Xu, Justin  and
      Johnson, Alistair  and
      Lin, Thomas  and
      Eyre, David  and
      Quispe, Rodolfo",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.bionlp-1.11/",
    pages = "115--127",
    ISBN = "979-8-89176-434-7",
    abstract = "De-identification systems prioritize recall to protect privacy, but excessive over-tagging reduces data utility. We propose an agentic refiner that reviews high-recall annotations using lightweight tools (validation functions, adaptive context retrieval, persistent to-do state, and modular review skills) to improve precision while minimizing recall loss. Experiments across three multilingual datasets show that the agent achieves significant improvements to binary precision. To support fine-grained analysis, we further introduce a synthetic error dataset of common and systemic failure modes, on which the agent corrects 99{\%} of injected errors in the medical datasets. Our results suggest that agent-based refinement provides a flexible and effective mechanism for improving de-identification precision as a modular extension to existing high-recall systems."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2026-post">
    <titleInfo>
        <title>Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alistair</namePart>
        <namePart type="family">Johnson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Eyre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rodolfo</namePart>
        <namePart type="family">Quispe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>BioNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dina</namePart>
            <namePart type="family">Demner-Fushman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophia</namePart>
            <namePart type="family">Ananiadou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kirk</namePart>
            <namePart type="family">Roberts</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Junichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-434-7</identifier>
    </relatedItem>
    <abstract>De-identification systems prioritize recall to protect privacy, but excessive over-tagging reduces data utility. We propose an agentic refiner that reviews high-recall annotations using lightweight tools (validation functions, adaptive context retrieval, persistent to-do state, and modular review skills) to improve precision while minimizing recall loss. Experiments across three multilingual datasets show that the agent achieves significant improvements to binary precision. To support fine-grained analysis, we further introduce a synthetic error dataset of common and systemic failure modes, on which the agent corrects 99% of injected errors in the medical datasets. Our results suggest that agent-based refinement provides a flexible and effective mechanism for improving de-identification precision as a modular extension to existing high-recall systems.</abstract>
    <identifier type="citekey">xu-etal-2026-post</identifier>
    <location>
        <url>https://aclanthology.org/2026.bionlp-1.11/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>115</start>
            <end>127</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification
%A Xu, Justin
%A Johnson, Alistair
%A Lin, Thomas
%A Eyre, David
%A Quispe, Rodolfo
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F xu-etal-2026-post
%X De-identification systems prioritize recall to protect privacy, but excessive over-tagging reduces data utility. We propose an agentic refiner that reviews high-recall annotations using lightweight tools (validation functions, adaptive context retrieval, persistent to-do state, and modular review skills) to improve precision while minimizing recall loss. Experiments across three multilingual datasets show that the agent achieves significant improvements to binary precision. To support fine-grained analysis, we further introduce a synthetic error dataset of common and systemic failure modes, on which the agent corrects 99% of injected errors in the medical datasets. Our results suggest that agent-based refinement provides a flexible and effective mechanism for improving de-identification precision as a modular extension to existing high-recall systems.
%U https://aclanthology.org/2026.bionlp-1.11/
%P 115-127

Download as File

Markdown (Informal)

[Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification](https://aclanthology.org/2026.bionlp-1.11/) (Xu et al., BioNLP 2026)

Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification (Xu et al., BioNLP 2026)

ACL

Justin Xu, Alistair Johnson, Thomas Lin, David Eyre, and Rodolfo Quispe. 2026. Post Hoc Agentic Refinement for Improving Precision in Multilingual Clinical Text De-identification. In BioNLP 2026, pages 115–127, San Diego, California. Association for Computational Linguistics.