Indic-Bias
Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes
About Dataset
We present Indic-Bias, a comprehensive benchmark to evaluate the fairness of LLMs across 85 Indian Identity groups, focusing on Bias and Stereotypes. We create three tasks - Plausibility, Judgment, and Generation, and evaluate 14 popular LLMs to identify allocative and representational harms.
Dataset Metadata
Attribution 4.0 International (CC BY- 4.0)
National
Sector Agnostic
Janki Atul Nawale and Mohammed Safi Ur Rahman Khan and Janani D and Mansi Gupta and Danish Pruthi and Mitesh M. Khapra
-
Structured
Static
NA
N.A.
10/07/25 04:42:32
Open
Hosted
Activity Overview
0
4 
24 
0
Tags
- Benchmark
- Bias Detection
- Indian Language
- Cultural Research
License Control
Attribution 4.0 International (CC BY- 4.0)
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.