Researchers have introduced NRITYAM, a new benchmark designed to assess the cultural understanding of language models, specifically within the domain of global dance traditions. This benchmark consists of 9,260 question-answer pairs across 12 languages, making it the largest dataset of its kind. Developed in collaboration with dance artists and native speakers, NRITYAM aims to set a new standard for evaluating how AI systems can comprehend and reason about traditional performing arts. AI
IMPACT This benchmark could lead to more culturally aware AI systems, improving their performance in diverse global contexts.
RANK_REASON The cluster describes a new academic paper introducing a benchmark dataset for evaluating language models.
- alphaXiv
- arXiv
- CatalyzeX
- CORE Recommender
- DagsHub
- dance
- Gotit.pub
- Hugging Face
- Language Models
- ScienceCast
- large language models
- multimodal large language models
- small language models
- small multimodal language models
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
