IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context
This work addresses the need for fairer LLM development in culturally diverse settings like India, though it is incremental as it builds on existing bias evaluation methods.
The authors tackled the problem of evaluating embedded biases in LLMs within the Indian context by proposing a contrastive learning-based framework and introducing the IndiCASA dataset with 2,575 validated sentences across five demographic axes, revealing that all tested models exhibit stereotypical biases, with disability biases being notably persistent.
Large Language Models (LLMs) have gained significant traction across critical domains owing to their impressive contextual understanding and generative capabilities. However, their increasing deployment in high stakes applications necessitates rigorous evaluation of embedded biases, particularly in culturally diverse contexts like India where existing embedding-based bias assessment methods often fall short in capturing nuanced stereotypes. We propose an evaluation framework based on a encoder trained using contrastive learning that captures fine-grained bias through embedding similarity. We also introduce a novel dataset - IndiCASA (IndiBias-based Contextually Aligned Stereotypes and Anti-stereotypes) comprising 2,575 human-validated sentences spanning five demographic axes: caste, gender, religion, disability, and socioeconomic status. Our evaluation of multiple open-weight LLMs reveals that all models exhibit some degree of stereotypical bias, with disability related biases being notably persistent, and religion bias generally lower likely due to global debiasing efforts demonstrating the need for fairer model development.