@inproceedings{thapa-etal-2025-probing,
title = "Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as {LLM} Benchmark for {AI} Wisdom",
author = "Thapa, Surendrabikram and
Rauniyar, Kritesh and
Veeramani, Hariram and
Adhikari, Surabhi and
Razzak, Imran and
Naseem, Usman",
editor = "Strube, Michael and
Braud, Chloe and
Hardmeier, Christian and
Li, Junyi Jessy and
Loaiciga, Sharid and
Zeldes, Amir and
Li, Chuyuan",
booktitle = "Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.codi-1.11/",
pages = "120--129",
ISBN = "979-8-89176-343-2",
abstract = "Understanding and interpreting culturally specific language remains a significant challenge for multilingual natural language processing (NLP) systems, particularly for less-resourced languages. To address this problem, this paper introduces PRONE, a novel dataset of 2,830 Nepali proverbs, and evaluates the performance of various language models (LMs) in two tasks: (i) identifying the correct meaning of a proverb from multiple choices, and (ii) categorizing proverbs into predefined thematic categories. The models, including both open-source and proprietary, were tested in zero-shot and few-shot settings with prompts in English and Nepali. While models like GPT-4o demonstrated promising results and achieved the highest performance among LMs, they still fall short of human-level accuracy in understanding and categorizing culturally nuanced content, highlighting the need for more inclusive NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thapa-etal-2025-probing">
<titleInfo>
<title>Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kritesh</namePart>
<namePart type="family">Rauniyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hariram</namePart>
<namePart type="family">Veeramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surabhi</namePart>
<namePart type="family">Adhikari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imran</namePart>
<namePart type="family">Razzak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</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>Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloe</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuyuan</namePart>
<namePart type="family">Li</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">979-8-89176-343-2</identifier>
</relatedItem>
<abstract>Understanding and interpreting culturally specific language remains a significant challenge for multilingual natural language processing (NLP) systems, particularly for less-resourced languages. To address this problem, this paper introduces PRONE, a novel dataset of 2,830 Nepali proverbs, and evaluates the performance of various language models (LMs) in two tasks: (i) identifying the correct meaning of a proverb from multiple choices, and (ii) categorizing proverbs into predefined thematic categories. The models, including both open-source and proprietary, were tested in zero-shot and few-shot settings with prompts in English and Nepali. While models like GPT-4o demonstrated promising results and achieved the highest performance among LMs, they still fall short of human-level accuracy in understanding and categorizing culturally nuanced content, highlighting the need for more inclusive NLP.</abstract>
<identifier type="citekey">thapa-etal-2025-probing</identifier>
<location>
<url>https://aclanthology.org/2025.codi-1.11/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>120</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom
%A Thapa, Surendrabikram
%A Rauniyar, Kritesh
%A Veeramani, Hariram
%A Adhikari, Surabhi
%A Razzak, Imran
%A Naseem, Usman
%Y Strube, Michael
%Y Braud, Chloe
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%Y Li, Chuyuan
%S Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-343-2
%F thapa-etal-2025-probing
%X Understanding and interpreting culturally specific language remains a significant challenge for multilingual natural language processing (NLP) systems, particularly for less-resourced languages. To address this problem, this paper introduces PRONE, a novel dataset of 2,830 Nepali proverbs, and evaluates the performance of various language models (LMs) in two tasks: (i) identifying the correct meaning of a proverb from multiple choices, and (ii) categorizing proverbs into predefined thematic categories. The models, including both open-source and proprietary, were tested in zero-shot and few-shot settings with prompts in English and Nepali. While models like GPT-4o demonstrated promising results and achieved the highest performance among LMs, they still fall short of human-level accuracy in understanding and categorizing culturally nuanced content, highlighting the need for more inclusive NLP.
%U https://aclanthology.org/2025.codi-1.11/
%P 120-129
Markdown (Informal)
[Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom](https://aclanthology.org/2025.codi-1.11/) (Thapa et al., CODI 2025)
ACL