SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maji, Arijit, Kumar, Raghvendra, Ghosh, Akash, Anushka, Saha, Sriparna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914117381521408
author Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Saha, Sriparna
author_facet Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Saha, Sriparna
contents Language Models (LMs) are indispensable tools shaping modern workflows, but their global effectiveness depends on understanding local socio-cultural contexts. To address this, we introduce SANSKRITI, a benchmark designed to evaluate language models' comprehension of India's rich cultural diversity. Comprising 21,853 meticulously curated question-answer pairs spanning 28 states and 8 union territories, SANSKRITI is the largest dataset for testing Indian cultural knowledge. It covers sixteen key attributes of Indian culture: rituals and ceremonies, history, tourism, cuisine, dance and music, costume, language, art, festivals, religion, medicine, transport, sports, nightlife, and personalities, providing a comprehensive representation of India's cultural tapestry. We evaluate SANSKRITI on leading Large Language Models (LLMs), Indic Language Models (ILMs), and Small Language Models (SLMs), revealing significant disparities in their ability to handle culturally nuanced queries, with many models struggling in region-specific contexts. By offering an extensive, culturally rich, and diverse dataset, SANSKRITI sets a new standard for assessing and improving the cultural understanding of LMs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15355
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture
Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Saha, Sriparna
Computation and Language
Language Models (LMs) are indispensable tools shaping modern workflows, but their global effectiveness depends on understanding local socio-cultural contexts. To address this, we introduce SANSKRITI, a benchmark designed to evaluate language models' comprehension of India's rich cultural diversity. Comprising 21,853 meticulously curated question-answer pairs spanning 28 states and 8 union territories, SANSKRITI is the largest dataset for testing Indian cultural knowledge. It covers sixteen key attributes of Indian culture: rituals and ceremonies, history, tourism, cuisine, dance and music, costume, language, art, festivals, religion, medicine, transport, sports, nightlife, and personalities, providing a comprehensive representation of India's cultural tapestry. We evaluate SANSKRITI on leading Large Language Models (LLMs), Indic Language Models (ILMs), and Small Language Models (SLMs), revealing significant disparities in their ability to handle culturally nuanced queries, with many models struggling in region-specific contexts. By offering an extensive, culturally rich, and diverse dataset, SANSKRITI sets a new standard for assessing and improving the cultural understanding of LMs.
title SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture
topic Computation and Language
url https://arxiv.org/abs/2506.15355