@inproceedings{pan-2026-aaa,
title = "{AAA} at {S}em{E}val-2026 Task 10: Psycholinguistic Conspiracy Marker Extraction and Detection",
author = "Pan, Xintong",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.250/",
pages = "1988--1991",
ISBN = "979-8-89176-414-9",
abstract = "This article presents our study on task 10: Psycholinguistic conspiracy marker extraction and detection, which includes token-level extraction tasks and sentence-level conspiracy detection tasks. Focusing on conspiracy theory texts on social media, this paper proposes a classification method that combines semantic encoding with large language model reasoning and generation. Semantic features are extracted using DeBERTa-v3, and explanatory reasoning text is generated through ConspEmoLLM-v2. The two are then combined for classification, thereby enhancing the model{'}s ability to recognize implicit conspiratorial logic. For the extraction subtask, this paper provides systematic comparison results of several mainstream pre-trained models, mainly conducting baseline model comparisons and performance analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-2026-aaa">
<titleInfo>
<title>AAA at SemEval-2026 Task 10: Psycholinguistic Conspiracy Marker Extraction and Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xintong</namePart>
<namePart type="family">Pan</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>This article presents our study on task 10: Psycholinguistic conspiracy marker extraction and detection, which includes token-level extraction tasks and sentence-level conspiracy detection tasks. Focusing on conspiracy theory texts on social media, this paper proposes a classification method that combines semantic encoding with large language model reasoning and generation. Semantic features are extracted using DeBERTa-v3, and explanatory reasoning text is generated through ConspEmoLLM-v2. The two are then combined for classification, thereby enhancing the model’s ability to recognize implicit conspiratorial logic. For the extraction subtask, this paper provides systematic comparison results of several mainstream pre-trained models, mainly conducting baseline model comparisons and performance analysis.</abstract>
<identifier type="citekey">pan-2026-aaa</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.250/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1988</start>
<end>1991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AAA at SemEval-2026 Task 10: Psycholinguistic Conspiracy Marker Extraction and Detection
%A Pan, Xintong
%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 pan-2026-aaa
%X This article presents our study on task 10: Psycholinguistic conspiracy marker extraction and detection, which includes token-level extraction tasks and sentence-level conspiracy detection tasks. Focusing on conspiracy theory texts on social media, this paper proposes a classification method that combines semantic encoding with large language model reasoning and generation. Semantic features are extracted using DeBERTa-v3, and explanatory reasoning text is generated through ConspEmoLLM-v2. The two are then combined for classification, thereby enhancing the model’s ability to recognize implicit conspiratorial logic. For the extraction subtask, this paper provides systematic comparison results of several mainstream pre-trained models, mainly conducting baseline model comparisons and performance analysis.
%U https://aclanthology.org/2026.semeval-1.250/
%P 1988-1991
Markdown (Informal)
[AAA at SemEval-2026 Task 10: Psycholinguistic Conspiracy Marker Extraction and Detection](https://aclanthology.org/2026.semeval-1.250/) (Pan, SemEval 2026)
ACL