@inproceedings{shrestha-etal-2026-necco,
title = "{N}e{CC}o: {N}epali Cultural Commonsense Benchmark for Large Language Model Evaluation",
author = "Shrestha, Sanket and
Regmi, Raunak and
Ghimire, Sadikshya and
Rana, Satyam and
Khadka, Supriya",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini",
booktitle = "Proceedings of the Second workshop on Challenges in Processing {S}outh {A}sian Languages ({CH}i{PSAL}2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.chipsal-1.15/",
doi = "10.63317/3zsmcs7pxtgi",
pages = "154--168",
abstract = "Large language models perform strongly on standard evaluations, yet these benchmarks prioritize high-resource languages and culturally dominant knowledge, leaving culture-specific commonsense underexamined. In low-resource languages such as Nepali, everyday communication depends on culturally embedded cues, including kinship hierarchies, ritual practices, food systems, idioms, and honorific distinctions that literal translation often fails to capture. As a result, models that appear competent on global metrics can perform poorly in local contexts. To address this gap, we introduce NeCCo, a curated multiple-choice benchmark for culturally situated reasoning across five domains: kinship and social hierarchy; festivals, rituals, and geography; idioms, proverbs, and metaphors; commonsense and daily life; and gastronomy, agriculture, and nature. The dataset was created through structured authoring, cross-review, and normalization, and is released in Devanagari, English, and Romanized formats. We evaluate multiple state-of-the-art LLMs using standardized prompting and controlled decoding. Results show substantial variation: models perform better on globally documented knowledge such as geography, but struggle with relational and linguistically implicit tasks, including extended kinship reasoning and proverb interpretation. The most culturally dense categories expose brittleness and increased hallucination. These findings suggest that multilingual competence requires more than translation coverage and highlight the need for culturally grounded benchmarks and training signals."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shrestha-etal-2026-necco">
<titleInfo>
<title>NeCCo: Nepali Cultural Commonsense Benchmark for Large Language Model Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanket</namePart>
<namePart type="family">Shrestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raunak</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadikshya</namePart>
<namePart type="family">Ghimire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satyam</namePart>
<namePart type="family">Rana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supriya</namePart>
<namePart type="family">Khadka</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 Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models perform strongly on standard evaluations, yet these benchmarks prioritize high-resource languages and culturally dominant knowledge, leaving culture-specific commonsense underexamined. In low-resource languages such as Nepali, everyday communication depends on culturally embedded cues, including kinship hierarchies, ritual practices, food systems, idioms, and honorific distinctions that literal translation often fails to capture. As a result, models that appear competent on global metrics can perform poorly in local contexts. To address this gap, we introduce NeCCo, a curated multiple-choice benchmark for culturally situated reasoning across five domains: kinship and social hierarchy; festivals, rituals, and geography; idioms, proverbs, and metaphors; commonsense and daily life; and gastronomy, agriculture, and nature. The dataset was created through structured authoring, cross-review, and normalization, and is released in Devanagari, English, and Romanized formats. We evaluate multiple state-of-the-art LLMs using standardized prompting and controlled decoding. Results show substantial variation: models perform better on globally documented knowledge such as geography, but struggle with relational and linguistically implicit tasks, including extended kinship reasoning and proverb interpretation. The most culturally dense categories expose brittleness and increased hallucination. These findings suggest that multilingual competence requires more than translation coverage and highlight the need for culturally grounded benchmarks and training signals.</abstract>
<identifier type="citekey">shrestha-etal-2026-necco</identifier>
<identifier type="doi">10.63317/3zsmcs7pxtgi</identifier>
<location>
<url>https://aclanthology.org/2026.chipsal-1.15/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>154</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NeCCo: Nepali Cultural Commonsense Benchmark for Large Language Model Evaluation
%A Shrestha, Sanket
%A Regmi, Raunak
%A Ghimire, Sadikshya
%A Rana, Satyam
%A Khadka, Supriya
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F shrestha-etal-2026-necco
%X Large language models perform strongly on standard evaluations, yet these benchmarks prioritize high-resource languages and culturally dominant knowledge, leaving culture-specific commonsense underexamined. In low-resource languages such as Nepali, everyday communication depends on culturally embedded cues, including kinship hierarchies, ritual practices, food systems, idioms, and honorific distinctions that literal translation often fails to capture. As a result, models that appear competent on global metrics can perform poorly in local contexts. To address this gap, we introduce NeCCo, a curated multiple-choice benchmark for culturally situated reasoning across five domains: kinship and social hierarchy; festivals, rituals, and geography; idioms, proverbs, and metaphors; commonsense and daily life; and gastronomy, agriculture, and nature. The dataset was created through structured authoring, cross-review, and normalization, and is released in Devanagari, English, and Romanized formats. We evaluate multiple state-of-the-art LLMs using standardized prompting and controlled decoding. Results show substantial variation: models perform better on globally documented knowledge such as geography, but struggle with relational and linguistically implicit tasks, including extended kinship reasoning and proverb interpretation. The most culturally dense categories expose brittleness and increased hallucination. These findings suggest that multilingual competence requires more than translation coverage and highlight the need for culturally grounded benchmarks and training signals.
%R 10.63317/3zsmcs7pxtgi
%U https://aclanthology.org/2026.chipsal-1.15/
%U https://doi.org/10.63317/3zsmcs7pxtgi
%P 154-168
Markdown (Informal)
[NeCCo: Nepali Cultural Commonsense Benchmark for Large Language Model Evaluation](https://aclanthology.org/2026.chipsal-1.15/) (Shrestha et al., CHiPSAL 2026)
ACL