LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining

Phuong Huu Vu Tran; Long Minh Vo; Son Nguyen Minh Le; Hoang Van

LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining

Phuong Huu Vu Tran, Long Minh Vo, Son Nguyen Minh Le, Hoang Van

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

We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions. The task requires paragraph-type classification, prediction of a subset of 141 official tags, and directed relation prediction under a strict JSON schema setting using only open-weight models up to 8B parameters. We frame the task as constrained structured prediction. The system first narrows the candidate tag space with metadata-aware dense retrieval, then applies constrained decoding with per-dimension caps, and escalates only uncertain cases to a three-agent debate branch.

Anthology ID:: 2026.argmining-1.11
Volume:: Proceedings of the 13th Workshop on Argument Mining and Reasoning
Month:: July
Year:: 2026
Address:: San Diego, California, USA
Editors:: Mohamed Elaraby, Annette Hautli-Janisz, Julia Romberg, Elena Musi, Federico Ruggeri, John Lawrence
Venues:: ArgMining | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 99–104
Language:
URL:: https://aclanthology.org/2026.argmining-1.11/
DOI:
Bibkey:
Cite (ACL):: Phuong Huu Vu Tran, Long Minh Vo, Son Nguyen Minh Le, and Hoang Van. 2026. LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining. In Proceedings of the 13th Workshop on Argument Mining and Reasoning, pages 99–104, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):: LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining (Tran et al., ArgMining 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.argmining-1.11.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{tran-etal-2026-llm,
    title = "{LLM}-{INSTRUCT} at {UZH} Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining",
    author = "Tran, Phuong Huu Vu  and
      Vo, Long Minh  and
      Le, Son Nguyen Minh  and
      Van, Hoang",
    editor = "Elaraby, Mohamed  and
      Hautli-Janisz, Annette  and
      Romberg, Julia  and
      Musi, Elena  and
      Ruggeri, Federico  and
      Lawrence, John",
    booktitle = "Proceedings of the 13th Workshop on Argument Mining and Reasoning",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.argmining-1.11/",
    pages = "99--104",
    ISBN = "979-8-89176-399-9",
    abstract = "We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions. The task requires paragraph-type classification, prediction of a subset of 141 official tags, and directed relation prediction under a strict JSON schema setting using only open-weight models up to 8B parameters. We frame the task as constrained structured prediction. The system first narrows the candidate tag space with metadata-aware dense retrieval, then applies constrained decoding with per-dimension caps, and escalates only uncertain cases to a three-agent debate branch."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2026-llm">
    <titleInfo>
        <title>LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Phuong</namePart>
        <namePart type="given">Huu</namePart>
        <namePart type="given">Vu</namePart>
        <namePart type="family">Tran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Long</namePart>
        <namePart type="given">Minh</namePart>
        <namePart type="family">Vo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Son</namePart>
        <namePart type="given">Nguyen</namePart>
        <namePart type="given">Minh</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hoang</namePart>
        <namePart type="family">Van</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>Proceedings of the 13th Workshop on Argument Mining and Reasoning</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohamed</namePart>
            <namePart type="family">Elaraby</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Annette</namePart>
            <namePart type="family">Hautli-Janisz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Romberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Elena</namePart>
            <namePart type="family">Musi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Federico</namePart>
            <namePart type="family">Ruggeri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">John</namePart>
            <namePart type="family">Lawrence</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-399-9</identifier>
    </relatedItem>
    <abstract>We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions. The task requires paragraph-type classification, prediction of a subset of 141 official tags, and directed relation prediction under a strict JSON schema setting using only open-weight models up to 8B parameters. We frame the task as constrained structured prediction. The system first narrows the candidate tag space with metadata-aware dense retrieval, then applies constrained decoding with per-dimension caps, and escalates only uncertain cases to a three-agent debate branch.</abstract>
    <identifier type="citekey">tran-etal-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.argmining-1.11/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>99</start>
            <end>104</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining
%A Tran, Phuong Huu Vu
%A Vo, Long Minh
%A Le, Son Nguyen Minh
%A Van, Hoang
%Y Elaraby, Mohamed
%Y Hautli-Janisz, Annette
%Y Romberg, Julia
%Y Musi, Elena
%Y Ruggeri, Federico
%Y Lawrence, John
%S Proceedings of the 13th Workshop on Argument Mining and Reasoning
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-399-9
%F tran-etal-2026-llm
%X We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions. The task requires paragraph-type classification, prediction of a subset of 141 official tags, and directed relation prediction under a strict JSON schema setting using only open-weight models up to 8B parameters. We frame the task as constrained structured prediction. The system first narrows the candidate tag space with metadata-aware dense retrieval, then applies constrained decoding with per-dimension caps, and escalates only uncertain cases to a three-agent debate branch.
%U https://aclanthology.org/2026.argmining-1.11/
%P 99-104

Download as File

Markdown (Informal)

[LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining](https://aclanthology.org/2026.argmining-1.11/) (Tran et al., ArgMining 2026)

LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining (Tran et al., ArgMining 2026)

ACL

Phuong Huu Vu Tran, Long Minh Vo, Son Nguyen Minh Le, and Hoang Van. 2026. LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining. In Proceedings of the 13th Workshop on Argument Mining and Reasoning, pages 99–104, San Diego, California, USA. Association for Computational Linguistics.