DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maji, Arijit, Kumar, Raghvendra, Ghosh, Akash, Anushka, Shah, Nemil, Borah, Abhilekh, Shah, Vanshika, Mishra, Nishant, Saha, Sriparna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915509563293696
author Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Shah, Nemil
Borah, Abhilekh
Shah, Vanshika
Mishra, Nishant
Saha, Sriparna
author_facet Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Shah, Nemil
Borah, Abhilekh
Shah, Vanshika
Mishra, Nishant
Saha, Sriparna
contents We introduce DRISHTIKON, a first-of-its-kind multimodal and multilingual benchmark centered exclusively on Indian culture, designed to evaluate the cultural understanding of generative AI systems. Unlike existing benchmarks with a generic or global scope, DRISHTIKON offers deep, fine-grained coverage across India's diverse regions, spanning 15 languages, covering all states and union territories, and incorporating over 64,000 aligned text-image pairs. The dataset captures rich cultural themes including festivals, attire, cuisines, art forms, and historical heritage amongst many more. We evaluate a wide range of vision-language models (VLMs), including open-source small and large models, proprietary systems, reasoning-specialized VLMs, and Indic-focused models, across zero-shot and chain-of-thought settings. Our results expose key limitations in current models' ability to reason over culturally grounded, multimodal inputs, particularly for low-resource languages and less-documented traditions. DRISHTIKON fills a vital gap in inclusive AI research, offering a robust testbed to advance culturally aware, multimodally competent language technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19274
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture
Maji, Arijit
Kumar, Raghvendra
Ghosh, Akash
Anushka
Shah, Nemil
Borah, Abhilekh
Shah, Vanshika
Mishra, Nishant
Saha, Sriparna
Computation and Language
Multimedia
We introduce DRISHTIKON, a first-of-its-kind multimodal and multilingual benchmark centered exclusively on Indian culture, designed to evaluate the cultural understanding of generative AI systems. Unlike existing benchmarks with a generic or global scope, DRISHTIKON offers deep, fine-grained coverage across India's diverse regions, spanning 15 languages, covering all states and union territories, and incorporating over 64,000 aligned text-image pairs. The dataset captures rich cultural themes including festivals, attire, cuisines, art forms, and historical heritage amongst many more. We evaluate a wide range of vision-language models (VLMs), including open-source small and large models, proprietary systems, reasoning-specialized VLMs, and Indic-focused models, across zero-shot and chain-of-thought settings. Our results expose key limitations in current models' ability to reason over culturally grounded, multimodal inputs, particularly for low-resource languages and less-documented traditions. DRISHTIKON fills a vital gap in inclusive AI research, offering a robust testbed to advance culturally aware, multimodally competent language technologies.
title DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture
topic Computation and Language
Multimedia
url https://arxiv.org/abs/2509.19274