@inproceedings{miah-etal-2025-hidden,
title = "Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of {LLM}s in Multimodal Settings",
author = "Miah, Md Messal Monem and
Anika, Adrita and
Shi, Xi and
Huang, Ruihong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1497/",
doi = "10.18653/v1/2025.acl-long.1497",
pages = "31013--31034",
ISBN = "979-8-89176-251-0",
abstract = "Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large Multimodal Models (LMMs) across diverse domains. We assess the performance of both open-source and proprietary LLMs on three distinct datasets{---}real-life trial interviews (RLTD), instructed deception in interpersonal scenarios (MU3D), and deceptive reviews (OpSpam). We systematically analyze the effectiveness of different experimental setups for deception detection, including zero-shot and few-shot approaches with random or similarity-based in-context example selection. Our findings indicate that fine-tuned LLMs achieve state-of-the-art performance on textual deception detection, whereas LMMs struggle to fully leverage multimodal cues, particularly in real-world settings. Additionally, we analyze the impact of auxiliary features, such as non-verbal gestures, video summaries, and evaluate the effectiveness of different promptingstrategies, such as direct label generation and post-hoc reasoning generation. Experiments unfold that reasoning-based predictions do not consistently improve performance over direct classification, contrary to the expectations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miah-etal-2025-hidden">
<titleInfo>
<title>Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Messal</namePart>
<namePart type="given">Monem</namePart>
<namePart type="family">Miah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrita</namePart>
<namePart type="family">Anika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large Multimodal Models (LMMs) across diverse domains. We assess the performance of both open-source and proprietary LLMs on three distinct datasets—real-life trial interviews (RLTD), instructed deception in interpersonal scenarios (MU3D), and deceptive reviews (OpSpam). We systematically analyze the effectiveness of different experimental setups for deception detection, including zero-shot and few-shot approaches with random or similarity-based in-context example selection. Our findings indicate that fine-tuned LLMs achieve state-of-the-art performance on textual deception detection, whereas LMMs struggle to fully leverage multimodal cues, particularly in real-world settings. Additionally, we analyze the impact of auxiliary features, such as non-verbal gestures, video summaries, and evaluate the effectiveness of different promptingstrategies, such as direct label generation and post-hoc reasoning generation. Experiments unfold that reasoning-based predictions do not consistently improve performance over direct classification, contrary to the expectations.</abstract>
<identifier type="citekey">miah-etal-2025-hidden</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1497</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1497/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>31013</start>
<end>31034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings
%A Miah, Md Messal Monem
%A Anika, Adrita
%A Shi, Xi
%A Huang, Ruihong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F miah-etal-2025-hidden
%X Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large Multimodal Models (LMMs) across diverse domains. We assess the performance of both open-source and proprietary LLMs on three distinct datasets—real-life trial interviews (RLTD), instructed deception in interpersonal scenarios (MU3D), and deceptive reviews (OpSpam). We systematically analyze the effectiveness of different experimental setups for deception detection, including zero-shot and few-shot approaches with random or similarity-based in-context example selection. Our findings indicate that fine-tuned LLMs achieve state-of-the-art performance on textual deception detection, whereas LMMs struggle to fully leverage multimodal cues, particularly in real-world settings. Additionally, we analyze the impact of auxiliary features, such as non-verbal gestures, video summaries, and evaluate the effectiveness of different promptingstrategies, such as direct label generation and post-hoc reasoning generation. Experiments unfold that reasoning-based predictions do not consistently improve performance over direct classification, contrary to the expectations.
%R 10.18653/v1/2025.acl-long.1497
%U https://aclanthology.org/2025.acl-long.1497/
%U https://doi.org/10.18653/v1/2025.acl-long.1497
%P 31013-31034
Markdown (Informal)
[Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal Settings](https://aclanthology.org/2025.acl-long.1497/) (Miah et al., ACL 2025)
ACL