<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishi-suzuki-2025-enhancing">
    <titleInfo>
        <title>Enhancing the Performance of Spoiler Review Detection by a LLM with Hints</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Genta</namePart>
        <namePart type="family">Nishi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Einoshin</namePart>
        <namePart type="family">Suzuki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alicia</namePart>
            <namePart type="family">Picazo-Izquierdo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ernesto</namePart>
            <namePart type="given">Luis</namePart>
            <namePart type="family">Estevanell-Valladares</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rafael</namePart>
            <namePart type="given">Muñoz</namePart>
            <namePart type="family">Guillena</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Raúl</namePart>
            <namePart type="given">García</namePart>
            <namePart type="family">Cerdá</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the effects of various hints including an introduction text, a few examples, and prompting techniques to enhance the performance of a Large-Language Model (LLM) in detecting a spoiler review of a movie. Detecting a spoiler review of a movie represents an important Natural Language Processing (NLP) task which resists the Deep Learning (DL) approach due to its highly subjective nature and scarcity in data. The highly subjective nature is also the main reason of the poor performance of LLMs-based methods, which explains their scarcity for the target problem. We address this problem by providing the LLM with an introduction text of the movie and a few reviews with their class labels as well as equipping it with a prompt that selects and exploits spoiler types with reasoning. Experiments using 400 manually labeled reviews and about 3200 LLM-labeled reviews show that our CAST (Clue And Select Types prompting) outperforms (0.05 higher) or is on par with (only 0.01 lower) cutting-edge LLM-based methods in three out of four movies in ROC-AUC. We believe our study represents an evidence of a target problem in which the knowledge intensive approach outperforms the learning-based approach.</abstract>
    <identifier type="citekey">nishi-suzuki-2025-enhancing</identifier>
    <location>
        <url>https://aclanthology.org/2025.r2lm-1.11/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>97</start>
            <end>112</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing the Performance of Spoiler Review Detection by a LLM with Hints
%A Nishi, Genta
%A Suzuki, Einoshin
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nishi-suzuki-2025-enhancing
%X We investigate the effects of various hints including an introduction text, a few examples, and prompting techniques to enhance the performance of a Large-Language Model (LLM) in detecting a spoiler review of a movie. Detecting a spoiler review of a movie represents an important Natural Language Processing (NLP) task which resists the Deep Learning (DL) approach due to its highly subjective nature and scarcity in data. The highly subjective nature is also the main reason of the poor performance of LLMs-based methods, which explains their scarcity for the target problem. We address this problem by providing the LLM with an introduction text of the movie and a few reviews with their class labels as well as equipping it with a prompt that selects and exploits spoiler types with reasoning. Experiments using 400 manually labeled reviews and about 3200 LLM-labeled reviews show that our CAST (Clue And Select Types prompting) outperforms (0.05 higher) or is on par with (only 0.01 lower) cutting-edge LLM-based methods in three out of four movies in ROC-AUC. We believe our study represents an evidence of a target problem in which the knowledge intensive approach outperforms the learning-based approach.
%U https://aclanthology.org/2025.r2lm-1.11/
%P 97-112

Markdown (Informal)

[Enhancing the Performance of Spoiler Review Detection by a LLM with Hints](https://aclanthology.org/2025.r2lm-1.11/) (Nishi & Suzuki, R2LM 2025)

• Enhancing the Performance of Spoiler Review Detection by a LLM with Hints (Nishi & Suzuki, R2LM 2025)

ACL

• Genta Nishi and Einoshin Suzuki. 2025. Enhancing the Performance of Spoiler Review Detection by a LLM with Hints. In Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models, pages 97–112, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.