@inproceedings{shafiei-etal-2026-truthtrap,
title = "{T}ruth{T}rap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering",
author = "Shafiei, Mohammadamin and
Saffari, Hamidreza and
Pilehvar, Mohammad Taher and
Raganato, Alessandro",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.155/",
pages = "2966--2987",
ISBN = "979-8-89176-386-9",
abstract = "Large Language Models (LLMs) are increasingly used to answer factual, information-seeking questions (ISQs). While prior work often focuses on false, misleading information, little attention has been paid to true but strategically persuasive content that can derail a model{'}s reasoning. To address this gap, we introduce a new evaluation dataset, TruthTrap, in two languages, i.e., English and Farsi, on Iran-related ISQs, each paired with a correct explanation and a persuasive-yet-misleading true hint. We then evaluate nine diverse LLMs (spanning proprietary and open-source systems) via factuality classification and multiple-choice QA tasks, finding that accuracy drops by 25{\%}, on average, when models encounter these misleading yet factual hints. Also, the models' predictions match the hint-aligned options up to 77 percent of the time. Notably, models often misjudge such hints in isolation yet still integrate them into final answers. Our results highlight a significant limitation in LLM outputs, underscoring the importance of robust fact-verification and emphasizing real-world risks posed by partial truths in domains like social media, education, and policy-making."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shafiei-etal-2026-truthtrap">
<titleInfo>
<title>TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammadamin</namePart>
<namePart type="family">Shafiei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamidreza</namePart>
<namePart type="family">Saffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) are increasingly used to answer factual, information-seeking questions (ISQs). While prior work often focuses on false, misleading information, little attention has been paid to true but strategically persuasive content that can derail a model’s reasoning. To address this gap, we introduce a new evaluation dataset, TruthTrap, in two languages, i.e., English and Farsi, on Iran-related ISQs, each paired with a correct explanation and a persuasive-yet-misleading true hint. We then evaluate nine diverse LLMs (spanning proprietary and open-source systems) via factuality classification and multiple-choice QA tasks, finding that accuracy drops by 25%, on average, when models encounter these misleading yet factual hints. Also, the models’ predictions match the hint-aligned options up to 77 percent of the time. Notably, models often misjudge such hints in isolation yet still integrate them into final answers. Our results highlight a significant limitation in LLM outputs, underscoring the importance of robust fact-verification and emphasizing real-world risks posed by partial truths in domains like social media, education, and policy-making.</abstract>
<identifier type="citekey">shafiei-etal-2026-truthtrap</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.155/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>2966</start>
<end>2987</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering
%A Shafiei, Mohammadamin
%A Saffari, Hamidreza
%A Pilehvar, Mohammad Taher
%A Raganato, Alessandro
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F shafiei-etal-2026-truthtrap
%X Large Language Models (LLMs) are increasingly used to answer factual, information-seeking questions (ISQs). While prior work often focuses on false, misleading information, little attention has been paid to true but strategically persuasive content that can derail a model’s reasoning. To address this gap, we introduce a new evaluation dataset, TruthTrap, in two languages, i.e., English and Farsi, on Iran-related ISQs, each paired with a correct explanation and a persuasive-yet-misleading true hint. We then evaluate nine diverse LLMs (spanning proprietary and open-source systems) via factuality classification and multiple-choice QA tasks, finding that accuracy drops by 25%, on average, when models encounter these misleading yet factual hints. Also, the models’ predictions match the hint-aligned options up to 77 percent of the time. Notably, models often misjudge such hints in isolation yet still integrate them into final answers. Our results highlight a significant limitation in LLM outputs, underscoring the importance of robust fact-verification and emphasizing real-world risks posed by partial truths in domains like social media, education, and policy-making.
%U https://aclanthology.org/2026.findings-eacl.155/
%P 2966-2987
Markdown (Informal)
[TruthTrap: A Bilingual Benchmark for Evaluating Factually Correct Yet Misleading Information in Question Answering](https://aclanthology.org/2026.findings-eacl.155/) (Shafiei et al., Findings 2026)
ACL