@inproceedings{song-etal-2026-spoiler,
title = "Spoiler Court: Interpretable Spoiler Detection via Adversarial Multi-Agent {LLM} Judgement",
author = "Song, Sangmin and
Kang, Hari and
Park, Suhyeon and
Choi, Seongwoo and
Im, Sungkyun and
Lee, Sangoh",
editor = "Bak, JinYeong and
van der Goot, Rob and
Jang, Hyeju and
Buaphet, Weerayut and
Ramponi, Alan and
Xu, Wei and
Ritter, Alan",
booktitle = "Proceedings of the 11th Workshop on Natural User-generated Text",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wnut-1.21/",
pages = "313--324",
ISBN = "979-8-89176-470-5",
abstract = "We present Spoiler Court, a multi-agent adversarial framework for interpretable spoiler detection in movie reviews. Three LLM agents, acting as the Plaintiff, Defendant, and Judge, engage in a multi-round courtroom debate to identify spoiler spans, challenge them, and deliver a final judgement with an interpretable audit trail grounded in the movie{'}s plot summary. Unlike prior work that produces only binary labels, Spoiler Court outputs which sentences are spoilers, why (via plot fact citations), and how the decision was reached (via adversarial debate transcripts). To evaluate the effectiveness of our approach, we construct a multi-genre evaluation dataset spanning 4 movies with binary and character-level span annotations. Under controlled conditions, Spoiler Court achieves an average F1 of 0.733 across 4 movies, outperforming other baselines including a dedicated spoiler detection framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2026-spoiler">
<titleInfo>
<title>Spoiler Court: Interpretable Spoiler Detection via Adversarial Multi-Agent LLM Judgement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sangmin</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hari</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhyeon</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongwoo</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungkyun</namePart>
<namePart type="family">Im</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangoh</namePart>
<namePart type="family">Lee</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 Natural User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">JinYeong</namePart>
<namePart type="family">Bak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeju</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weerayut</namePart>
<namePart type="family">Buaphet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ramponi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</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">979-8-89176-470-5</identifier>
</relatedItem>
<abstract>We present Spoiler Court, a multi-agent adversarial framework for interpretable spoiler detection in movie reviews. Three LLM agents, acting as the Plaintiff, Defendant, and Judge, engage in a multi-round courtroom debate to identify spoiler spans, challenge them, and deliver a final judgement with an interpretable audit trail grounded in the movie’s plot summary. Unlike prior work that produces only binary labels, Spoiler Court outputs which sentences are spoilers, why (via plot fact citations), and how the decision was reached (via adversarial debate transcripts). To evaluate the effectiveness of our approach, we construct a multi-genre evaluation dataset spanning 4 movies with binary and character-level span annotations. Under controlled conditions, Spoiler Court achieves an average F1 of 0.733 across 4 movies, outperforming other baselines including a dedicated spoiler detection framework.</abstract>
<identifier type="citekey">song-etal-2026-spoiler</identifier>
<location>
<url>https://aclanthology.org/2026.wnut-1.21/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>313</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spoiler Court: Interpretable Spoiler Detection via Adversarial Multi-Agent LLM Judgement
%A Song, Sangmin
%A Kang, Hari
%A Park, Suhyeon
%A Choi, Seongwoo
%A Im, Sungkyun
%A Lee, Sangoh
%Y Bak, JinYeong
%Y van der Goot, Rob
%Y Jang, Hyeju
%Y Buaphet, Weerayut
%Y Ramponi, Alan
%Y Xu, Wei
%Y Ritter, Alan
%S Proceedings of the 11th Workshop on Natural User-generated Text
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-470-5
%F song-etal-2026-spoiler
%X We present Spoiler Court, a multi-agent adversarial framework for interpretable spoiler detection in movie reviews. Three LLM agents, acting as the Plaintiff, Defendant, and Judge, engage in a multi-round courtroom debate to identify spoiler spans, challenge them, and deliver a final judgement with an interpretable audit trail grounded in the movie’s plot summary. Unlike prior work that produces only binary labels, Spoiler Court outputs which sentences are spoilers, why (via plot fact citations), and how the decision was reached (via adversarial debate transcripts). To evaluate the effectiveness of our approach, we construct a multi-genre evaluation dataset spanning 4 movies with binary and character-level span annotations. Under controlled conditions, Spoiler Court achieves an average F1 of 0.733 across 4 movies, outperforming other baselines including a dedicated spoiler detection framework.
%U https://aclanthology.org/2026.wnut-1.21/
%P 313-324
Markdown (Informal)
[Spoiler Court: Interpretable Spoiler Detection via Adversarial Multi-Agent LLM Judgement](https://aclanthology.org/2026.wnut-1.21/) (Song et al., WNUT 2026)
ACL