@inproceedings{hosseini-etal-2026-ffe,
title = "{FFE}-Hallu: Hallucinations in Fixed Figurative Expressions: A Benchmark of Idioms and Proverbs in the {P}ersian Language",
author = "Hosseini, Faezeh and
Yousefzadeh, Mohammadali and
Yaghoobzadeh, Yadollah",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.241/",
pages = "5222--5235",
ISBN = "979-8-89176-380-7",
abstract = "Figurative language, especially fixed figurative expressions (FFEs) such as idioms and proverbs, poses unique challenges for large language models (LLMs). Unlike literal phrases, FFEs are culturally grounded and often non-compositional, making them vulnerable to figurative hallucination, the generation or acceptance of plausible-sounding but culturally invalid expressions. We introduce \textbf{FFE-Hallu}, the first comprehensive benchmark for evaluating LLMs' ability to generate, detect, and translate FFEs in Persian, a linguistically rich but underrepresented language. FFE-Hallu includes 600 carefully curated examples spanning three tasks: FFE generation from meaning, detection of fabricated FFEs (across four controlled categories), and FFE-to-FFE translation from English to Persian. Our evaluation of six state-of-the-art multilingual LLMs reveals persistent weaknesses in both cultural grounding and figurative competence. While models like GPT-4.1 display relative strength in rejecting fabricated FFEs and retrieving authentic ones, most systems struggle to reliably distinguish real FFEs from high-quality fabrications and often hallucinate in translation. This work shows that LLMs still have important gaps in understanding and using figurative language, and that specialized benchmarks like FFE-Hallu are needed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hosseini-etal-2026-ffe">
<titleInfo>
<title>FFE-Hallu: Hallucinations in Fixed Figurative Expressions: A Benchmark of Idioms and Proverbs in the Persian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faezeh</namePart>
<namePart type="family">Hosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadali</namePart>
<namePart type="family">Yousefzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadollah</namePart>
<namePart type="family">Yaghoobzadeh</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>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Figurative language, especially fixed figurative expressions (FFEs) such as idioms and proverbs, poses unique challenges for large language models (LLMs). Unlike literal phrases, FFEs are culturally grounded and often non-compositional, making them vulnerable to figurative hallucination, the generation or acceptance of plausible-sounding but culturally invalid expressions. We introduce FFE-Hallu, the first comprehensive benchmark for evaluating LLMs’ ability to generate, detect, and translate FFEs in Persian, a linguistically rich but underrepresented language. FFE-Hallu includes 600 carefully curated examples spanning three tasks: FFE generation from meaning, detection of fabricated FFEs (across four controlled categories), and FFE-to-FFE translation from English to Persian. Our evaluation of six state-of-the-art multilingual LLMs reveals persistent weaknesses in both cultural grounding and figurative competence. While models like GPT-4.1 display relative strength in rejecting fabricated FFEs and retrieving authentic ones, most systems struggle to reliably distinguish real FFEs from high-quality fabrications and often hallucinate in translation. This work shows that LLMs still have important gaps in understanding and using figurative language, and that specialized benchmarks like FFE-Hallu are needed.</abstract>
<identifier type="citekey">hosseini-etal-2026-ffe</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.241/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>5222</start>
<end>5235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FFE-Hallu: Hallucinations in Fixed Figurative Expressions: A Benchmark of Idioms and Proverbs in the Persian Language
%A Hosseini, Faezeh
%A Yousefzadeh, Mohammadali
%A Yaghoobzadeh, Yadollah
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F hosseini-etal-2026-ffe
%X Figurative language, especially fixed figurative expressions (FFEs) such as idioms and proverbs, poses unique challenges for large language models (LLMs). Unlike literal phrases, FFEs are culturally grounded and often non-compositional, making them vulnerable to figurative hallucination, the generation or acceptance of plausible-sounding but culturally invalid expressions. We introduce FFE-Hallu, the first comprehensive benchmark for evaluating LLMs’ ability to generate, detect, and translate FFEs in Persian, a linguistically rich but underrepresented language. FFE-Hallu includes 600 carefully curated examples spanning three tasks: FFE generation from meaning, detection of fabricated FFEs (across four controlled categories), and FFE-to-FFE translation from English to Persian. Our evaluation of six state-of-the-art multilingual LLMs reveals persistent weaknesses in both cultural grounding and figurative competence. While models like GPT-4.1 display relative strength in rejecting fabricated FFEs and retrieving authentic ones, most systems struggle to reliably distinguish real FFEs from high-quality fabrications and often hallucinate in translation. This work shows that LLMs still have important gaps in understanding and using figurative language, and that specialized benchmarks like FFE-Hallu are needed.
%U https://aclanthology.org/2026.eacl-long.241/
%P 5222-5235
Markdown (Informal)
[FFE-Hallu: Hallucinations in Fixed Figurative Expressions: A Benchmark of Idioms and Proverbs in the Persian Language](https://aclanthology.org/2026.eacl-long.241/) (Hosseini et al., EACL 2026)
ACL