<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peerachaidecho-rutherford-2026-chulanlp">
    <titleInfo>
        <title>ChulaNLP at SemEval-2026 Task 6: A Hybrid BERT-LLM Framework for Political Response Clarity and Evasion Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wisarut</namePart>
        <namePart type="family">Peerachaidecho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Attapol</namePart>
        <namePart type="family">Rutherford</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 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</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">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>SemEval-2026 Task 6 (CLARITY: Unmasking Political Interview) focuses on detecting equivocation and evasion techniques in political interviews. While encoder-only models and Large Language Models (LLMs) individually struggle with this task, we propose a hybrid BERT–LLM framework to leverage their complementary strengths: the discriminative efficiency of fine-tuned encoders and the sophisticated reasoning of LLMs. We benchmarked several long-context architectures—DeBERTa, RooseBERT, and BigBird—finding that a truncated DeBERTa-large provided the most reliable candidates for the LLM. By using DeBERTa’s top-5 predicted labels as constrained options for LLM inference, we significantly improved evasion-level classification. This hybrid approach achieved competitive rankings in the shared task, placing 7th in Subtask 1 and 2nd in Subtask 2.</abstract>
    <identifier type="citekey">peerachaidecho-rutherford-2026-chulanlp</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.236/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1874</start>
            <end>1881</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ChulaNLP at SemEval-2026 Task 6: A Hybrid BERT-LLM Framework for Political Response Clarity and Evasion Detection
%A Peerachaidecho, Wisarut
%A Rutherford, Attapol
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F peerachaidecho-rutherford-2026-chulanlp
%X SemEval-2026 Task 6 (CLARITY: Unmasking Political Interview) focuses on detecting equivocation and evasion techniques in political interviews. While encoder-only models and Large Language Models (LLMs) individually struggle with this task, we propose a hybrid BERT–LLM framework to leverage their complementary strengths: the discriminative efficiency of fine-tuned encoders and the sophisticated reasoning of LLMs. We benchmarked several long-context architectures—DeBERTa, RooseBERT, and BigBird—finding that a truncated DeBERTa-large provided the most reliable candidates for the LLM. By using DeBERTa’s top-5 predicted labels as constrained options for LLM inference, we significantly improved evasion-level classification. This hybrid approach achieved competitive rankings in the shared task, placing 7th in Subtask 1 and 2nd in Subtask 2.
%U https://aclanthology.org/2026.semeval-1.236/
%P 1874-1881

Markdown (Informal)

[ChulaNLP at SemEval-2026 Task 6: A Hybrid BERT-LLM Framework for Political Response Clarity and Evasion Detection](https://aclanthology.org/2026.semeval-1.236/) (Peerachaidecho & Rutherford, SemEval 2026)

• ChulaNLP at SemEval-2026 Task 6: A Hybrid BERT-LLM Framework for Political Response Clarity and Evasion Detection (Peerachaidecho & Rutherford, SemEval 2026)

ACL

• Wisarut Peerachaidecho and Attapol Rutherford. 2026. ChulaNLP at SemEval-2026 Task 6: A Hybrid BERT-LLM Framework for Political Response Clarity and Evasion Detection. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1874–1881, San Diego, California, USA. Association for Computational Linguistics.