<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-karma">
    <titleInfo>
        <title>KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinkyeong</namePart>
        <namePart type="family">Choi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chaebin</namePart>
        <namePart type="family">Jeong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Donghyeon</namePart>
        <namePart type="family">Park</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>Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Problem and propose KARMA, which enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates. Slot-Parallel Alignment (SPA) then applies a decoupled slot-level objective to route preference supervision to discriminative entity-slots, with slot-aware masked attention serving as an optional packed-evaluation implementation. Across biomedical, computer-science, and chemistry benchmarks, KARMA outperforms base LLM and same-data SFT baselines, and compares favorably with sequence- and token-level preference methods.</abstract>
    <identifier type="citekey">choi-etal-2026-karma</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.970</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.970/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>20513</start>
            <end>20531</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment
%A Choi, Jinkyeong
%A Jeong, Chaebin
%A Park, Donghyeon
%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 choi-etal-2026-karma
%X Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Problem and propose KARMA, which enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates. Slot-Parallel Alignment (SPA) then applies a decoupled slot-level objective to route preference supervision to discriminative entity-slots, with slot-aware masked attention serving as an optional packed-evaluation implementation. Across biomedical, computer-science, and chemistry benchmarks, KARMA outperforms base LLM and same-data SFT baselines, and compares favorably with sequence- and token-level preference methods.
%R 10.18653/2026.findings-emnlp.970
%U https://aclanthology.org/2026.findings-emnlp.970/
%U https://doi.org/10.18653/2026.findings-emnlp.970
%P 20513-20531

Markdown (Informal)

[KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment](https://aclanthology.org/2026.findings-emnlp.970/) (Choi et al., Findings 2026)

• KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment (Choi et al., Findings 2026)

ACL

• Jinkyeong Choi, Chaebin Jeong, and Donghyeon Park. 2026. KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 20513–20531, Budapest, Hungary. Association for Computational Linguistics.