@inproceedings{thmer-etal-2026-beyond,
title = "Beyond Literal Meaning: How {LLM}s Interpret Yemeni Proverbs",
author = "Thmer, Nasser and
Al-Laith, Ali and
Shoaib, Muhammad",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.83/",
doi = "10.63317/4hxnxxxq5iu2",
pages = "1071--1080",
abstract = "We present a benchmark Yemeni proverbs dataset paired with expert-annotated explanations, designed to evaluate the cultural reasoning abilities of large language models (LLMs). Using zero-shot and few-shot prompting, we assess seven LLMs through both automatic and human evaluation. Results show that instruction-tuned models like GPT-4o and Gemini 1.5 Pro outperform smaller models in both automatic and human evaluations. Few-shot prompting significantly improves performance across all models, underscoring its value for figurative and culturally grounded language tasks. Notably, ALLaM, a bilingual model trained on Arabic and English, achieves competitive results, demonstrating the potential of regionally adapted models for low-resource cultural tasks. LLM-as-a-Judge evaluation correlates strongly with human assessment (Kendall{'}s {\ensuremath{\tau}} up to 0.98). Error analysis identifies recurring literal interpretation and cultural misalignment as key failure modes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thmer-etal-2026-beyond">
<titleInfo>
<title>Beyond Literal Meaning: How LLMs Interpret Yemeni Proverbs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasser</namePart>
<namePart type="family">Thmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Laith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Shoaib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a benchmark Yemeni proverbs dataset paired with expert-annotated explanations, designed to evaluate the cultural reasoning abilities of large language models (LLMs). Using zero-shot and few-shot prompting, we assess seven LLMs through both automatic and human evaluation. Results show that instruction-tuned models like GPT-4o and Gemini 1.5 Pro outperform smaller models in both automatic and human evaluations. Few-shot prompting significantly improves performance across all models, underscoring its value for figurative and culturally grounded language tasks. Notably, ALLaM, a bilingual model trained on Arabic and English, achieves competitive results, demonstrating the potential of regionally adapted models for low-resource cultural tasks. LLM-as-a-Judge evaluation correlates strongly with human assessment (Kendall’s \ensuremathτ up to 0.98). Error analysis identifies recurring literal interpretation and cultural misalignment as key failure modes.</abstract>
<identifier type="citekey">thmer-etal-2026-beyond</identifier>
<identifier type="doi">10.63317/4hxnxxxq5iu2</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.83/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1071</start>
<end>1080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Literal Meaning: How LLMs Interpret Yemeni Proverbs
%A Thmer, Nasser
%A Al-Laith, Ali
%A Shoaib, Muhammad
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F thmer-etal-2026-beyond
%X We present a benchmark Yemeni proverbs dataset paired with expert-annotated explanations, designed to evaluate the cultural reasoning abilities of large language models (LLMs). Using zero-shot and few-shot prompting, we assess seven LLMs through both automatic and human evaluation. Results show that instruction-tuned models like GPT-4o and Gemini 1.5 Pro outperform smaller models in both automatic and human evaluations. Few-shot prompting significantly improves performance across all models, underscoring its value for figurative and culturally grounded language tasks. Notably, ALLaM, a bilingual model trained on Arabic and English, achieves competitive results, demonstrating the potential of regionally adapted models for low-resource cultural tasks. LLM-as-a-Judge evaluation correlates strongly with human assessment (Kendall’s \ensuremathτ up to 0.98). Error analysis identifies recurring literal interpretation and cultural misalignment as key failure modes.
%R 10.63317/4hxnxxxq5iu2
%U https://aclanthology.org/2026.lrec-1.83/
%U https://doi.org/10.63317/4hxnxxxq5iu2
%P 1071-1080
Markdown (Informal)
[Beyond Literal Meaning: How LLMs Interpret Yemeni Proverbs](https://aclanthology.org/2026.lrec-1.83/) (Thmer et al., LREC 2026)
ACL