@inproceedings{carabas-etal-2026-psy,
title = "psy detectives at {S}em{E}val-2026 Task 10: {P}sy{C}o{M}ark {--} Psycholinguistic Conspiracy Marker Extraction and Detection",
author = "Carabas, Roxana and
Nacu, Anamaria and
Isac, Lucian and
Gifu, Daniela",
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-1.1/",
pages = "1--7",
ISBN = "979-8-89176-414-9",
abstract = "We present our SemEval-2026 Task 10 (PsyCoMark) system that combines interpretable psycholinguistic signals with supervised neural modeling. Our approach includes (1) a marker-derived lexicon and LIWC-style ratio features built from span annotations, (2) binary Yes/No transformer baselines (RoBERTa and DeBERTa families) with optimized training configurations, and (3) a zero-shot TinyLlama-1.1B baseline for the full three-way setting (Yes/No/Can{'}t tell). Results show that marker-only features are transparent but weak, while transformer models provide substantially stronger performance; the best model, DeBERTa-v3-large, achieves 0.8339 weighted F1 on development and 0.75 weighted F1 on the competition test set. We also evaluate marker-driven heuristic relabeling of uncertain instances, which does not improve downstream performance. Overall, the submission provides a controlled, interpretable, and reproducible reference point for future work on integrating span-level psycholinguistic evidence with conspiracy detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carabas-etal-2026-psy">
<titleInfo>
<title>psy detectives at SemEval-2026 Task 10: PsyCoMark – Psycholinguistic Conspiracy Marker Extraction and Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roxana</namePart>
<namePart type="family">Carabas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anamaria</namePart>
<namePart type="family">Nacu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucian</namePart>
<namePart type="family">Isac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Gifu</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>We present our SemEval-2026 Task 10 (PsyCoMark) system that combines interpretable psycholinguistic signals with supervised neural modeling. Our approach includes (1) a marker-derived lexicon and LIWC-style ratio features built from span annotations, (2) binary Yes/No transformer baselines (RoBERTa and DeBERTa families) with optimized training configurations, and (3) a zero-shot TinyLlama-1.1B baseline for the full three-way setting (Yes/No/Can’t tell). Results show that marker-only features are transparent but weak, while transformer models provide substantially stronger performance; the best model, DeBERTa-v3-large, achieves 0.8339 weighted F1 on development and 0.75 weighted F1 on the competition test set. We also evaluate marker-driven heuristic relabeling of uncertain instances, which does not improve downstream performance. Overall, the submission provides a controlled, interpretable, and reproducible reference point for future work on integrating span-level psycholinguistic evidence with conspiracy detection.</abstract>
<identifier type="citekey">carabas-etal-2026-psy</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.1/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T psy detectives at SemEval-2026 Task 10: PsyCoMark – Psycholinguistic Conspiracy Marker Extraction and Detection
%A Carabas, Roxana
%A Nacu, Anamaria
%A Isac, Lucian
%A Gifu, Daniela
%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 carabas-etal-2026-psy
%X We present our SemEval-2026 Task 10 (PsyCoMark) system that combines interpretable psycholinguistic signals with supervised neural modeling. Our approach includes (1) a marker-derived lexicon and LIWC-style ratio features built from span annotations, (2) binary Yes/No transformer baselines (RoBERTa and DeBERTa families) with optimized training configurations, and (3) a zero-shot TinyLlama-1.1B baseline for the full three-way setting (Yes/No/Can’t tell). Results show that marker-only features are transparent but weak, while transformer models provide substantially stronger performance; the best model, DeBERTa-v3-large, achieves 0.8339 weighted F1 on development and 0.75 weighted F1 on the competition test set. We also evaluate marker-driven heuristic relabeling of uncertain instances, which does not improve downstream performance. Overall, the submission provides a controlled, interpretable, and reproducible reference point for future work on integrating span-level psycholinguistic evidence with conspiracy detection.
%U https://aclanthology.org/2026.semeval-1.1/
%P 1-7
Markdown (Informal)
[psy detectives at SemEval-2026 Task 10: PsyCoMark – Psycholinguistic Conspiracy Marker Extraction and Detection](https://aclanthology.org/2026.semeval-1.1/) (Carabas et al., SemEval 2026)
ACL