@inproceedings{nobakhtian-etal-2025-evaluating,
title = "Evaluating Cultural Knowledge and Reasoning in {LLM}s Through {P}ersian Allusions",
author = "Nobakhtian, Melika and
Yaghoobzadeh, Yadollah and
Pilehvar, Mohammad Taher",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1403/",
pages = "25725--25737",
ISBN = "979-8-89176-335-7",
abstract = "Allusion recognition{---}a task demanding contextual activation of cultural knowledge{---}serves as a critical test of LLMs' ability to deploy stored information in open-ended, figurative settings. We introduce a framework for evaluating Persian literary allusions through (1) classical poetry annotations and (2) LLM-generated texts incorporating allusions in novel contexts. By combining knowledge assessments, multiple-choice tasks, and open-ended recognition, we analyze whether failures stem from knowledge gaps or activation challenges. Evaluations across eleven LLMs highlight a notable observation: models exhibit strong foundational knowledge and high multiple-choice accuracy, yet performance drops substantially in open-ended tasks, especially for indirect references. Reasoning-optimized models generalize better to novel contexts, whereas distilled models show marked degradation in cultural reasoning. The gap underscores that LLMs' limitations arise not from missing knowledge but from difficulties in spontaneously activating cultural references without explicit cues. We propose allusion recognition as a benchmark for contextual knowledge deployment, highlighting the need for training paradigms that bridge factual recall and culturally grounded reasoning. Our code, datasets and results are available at https://github.com/MelikaNobakhtian/Allusion"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nobakhtian-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Cultural Knowledge and Reasoning in LLMs Through Persian Allusions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Melika</namePart>
<namePart type="family">Nobakhtian</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>
<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>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Allusion recognition—a task demanding contextual activation of cultural knowledge—serves as a critical test of LLMs’ ability to deploy stored information in open-ended, figurative settings. We introduce a framework for evaluating Persian literary allusions through (1) classical poetry annotations and (2) LLM-generated texts incorporating allusions in novel contexts. By combining knowledge assessments, multiple-choice tasks, and open-ended recognition, we analyze whether failures stem from knowledge gaps or activation challenges. Evaluations across eleven LLMs highlight a notable observation: models exhibit strong foundational knowledge and high multiple-choice accuracy, yet performance drops substantially in open-ended tasks, especially for indirect references. Reasoning-optimized models generalize better to novel contexts, whereas distilled models show marked degradation in cultural reasoning. The gap underscores that LLMs’ limitations arise not from missing knowledge but from difficulties in spontaneously activating cultural references without explicit cues. We propose allusion recognition as a benchmark for contextual knowledge deployment, highlighting the need for training paradigms that bridge factual recall and culturally grounded reasoning. Our code, datasets and results are available at https://github.com/MelikaNobakhtian/Allusion</abstract>
<identifier type="citekey">nobakhtian-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1403/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>25725</start>
<end>25737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Cultural Knowledge and Reasoning in LLMs Through Persian Allusions
%A Nobakhtian, Melika
%A Yaghoobzadeh, Yadollah
%A Pilehvar, Mohammad Taher
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F nobakhtian-etal-2025-evaluating
%X Allusion recognition—a task demanding contextual activation of cultural knowledge—serves as a critical test of LLMs’ ability to deploy stored information in open-ended, figurative settings. We introduce a framework for evaluating Persian literary allusions through (1) classical poetry annotations and (2) LLM-generated texts incorporating allusions in novel contexts. By combining knowledge assessments, multiple-choice tasks, and open-ended recognition, we analyze whether failures stem from knowledge gaps or activation challenges. Evaluations across eleven LLMs highlight a notable observation: models exhibit strong foundational knowledge and high multiple-choice accuracy, yet performance drops substantially in open-ended tasks, especially for indirect references. Reasoning-optimized models generalize better to novel contexts, whereas distilled models show marked degradation in cultural reasoning. The gap underscores that LLMs’ limitations arise not from missing knowledge but from difficulties in spontaneously activating cultural references without explicit cues. We propose allusion recognition as a benchmark for contextual knowledge deployment, highlighting the need for training paradigms that bridge factual recall and culturally grounded reasoning. Our code, datasets and results are available at https://github.com/MelikaNobakhtian/Allusion
%U https://aclanthology.org/2025.findings-emnlp.1403/
%P 25725-25737
Markdown (Informal)
[Evaluating Cultural Knowledge and Reasoning in LLMs Through Persian Allusions](https://aclanthology.org/2025.findings-emnlp.1403/) (Nobakhtian et al., Findings 2025)
ACL