<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prasanna-etal-2026-langkg">
    <titleInfo>
        <title>LangKG at the FinEval 2026: Answer-Contract Knowledge over Instruction Engineering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shivika</namePart>
        <namePart type="family">Prasanna</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaeseong</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yourong</namePart>
        <namePart type="family">Xu</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>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jimin</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yongjae</namePart>
            <namePart type="family">Lee</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">Hsin-Hsi</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chung-Chi</namePart>
            <namePart type="family">Chen</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">979-8-89176-466-8</identifier>
    </relatedItem>
    <abstract>Automated multilingual financial question answering requires models to synthesize evidence across SEC filing statements and parallel news reporting in five languages, grounding every claim in aligned, verifiable source material. We participate in the FinNLP 2026 Shared Task (FinEval 2026) Subtask 3, built on the challenging MultiFinBen/PolyFiQA benchmark, under a strict 70-billion-parameter constraint and a Macro-averaged ROUGE-1 F1 evaluation metric. We find that shared task’s practice (train) and test splits encode an inverted query-answer contract, and highly specific prompt engineering tuned against one split overfits and fails to transfer to the other. Motivated by this, we introduce an explicit answer-contract knowledge policy encoding evidence-boundedness, multilingual evidence alignment, exact-value preservation, reporting-period disambiguation, and intentional non-response, and implement it through two complementary generation strategies: Chain-of-Verification (CoVe) and Prompt-variant ensembling with heuristic re-ranking. Our submitted system (ensembling) improves over direct-prompting baseline and CoVe (0.41 to 0.49 ROUGE-1 F1 over train set) and achieves 0.324 ROUGE-1 F1 on the shared task’s leaderboard, ranking 11 of 15 teams.</abstract>
    <identifier type="citekey">prasanna-etal-2026-langkg</identifier>
    <location>
        <url>https://aclanthology.org/2026.finnlp-1.71/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>793</start>
            <end>799</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LangKG at the FinEval 2026: Answer-Contract Knowledge over Instruction Engineering
%A Prasanna, Shivika
%A Lee, Jaeseong
%A Su, Hui
%A Xu, Yourong
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F prasanna-etal-2026-langkg
%X Automated multilingual financial question answering requires models to synthesize evidence across SEC filing statements and parallel news reporting in five languages, grounding every claim in aligned, verifiable source material. We participate in the FinNLP 2026 Shared Task (FinEval 2026) Subtask 3, built on the challenging MultiFinBen/PolyFiQA benchmark, under a strict 70-billion-parameter constraint and a Macro-averaged ROUGE-1 F1 evaluation metric. We find that shared task’s practice (train) and test splits encode an inverted query-answer contract, and highly specific prompt engineering tuned against one split overfits and fails to transfer to the other. Motivated by this, we introduce an explicit answer-contract knowledge policy encoding evidence-boundedness, multilingual evidence alignment, exact-value preservation, reporting-period disambiguation, and intentional non-response, and implement it through two complementary generation strategies: Chain-of-Verification (CoVe) and Prompt-variant ensembling with heuristic re-ranking. Our submitted system (ensembling) improves over direct-prompting baseline and CoVe (0.41 to 0.49 ROUGE-1 F1 over train set) and achieves 0.324 ROUGE-1 F1 on the shared task’s leaderboard, ranking 11 of 15 teams.
%U https://aclanthology.org/2026.finnlp-1.71/
%P 793-799

Markdown (Informal)

[LangKG at the FinEval 2026: Answer-Contract Knowledge over Instruction Engineering](https://aclanthology.org/2026.finnlp-1.71/) (Prasanna et al., FinNLP 2026)

• LangKG at the FinEval 2026: Answer-Contract Knowledge over Instruction Engineering (Prasanna et al., FinNLP 2026)

ACL

• Shivika Prasanna, Jaeseong Lee, Hui Su, and Yourong Xu. 2026. LangKG at the FinEval 2026: Answer-Contract Knowledge over Instruction Engineering. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 793–799, Budapest, Hungary. Association for Computational Linguistics.