Research Areas

Legal NLP

The judicial systems across the globe are not just overloaded with the number of cases but deal with numerous other challenges like information overload, inefficiency in case research, limited accessibility for non-legal experts, bias and lack of transparency, to name a few.

Indian Sign Language

When words are out of reach, the hands sing—sign language is the art of giving silence its voice.

Machine Unlearning

LLMs tend to memorize information including PI information leading to privacy issues. Machine Unlearning is a new setup wherein a pretrained model is made to "forget" certain information regarding some users who request their data to be removed.

Affective Computing

Language and vocabulary have emerged from emotions that were perceived. In this research we try to walk backwards to analyse emotions from language.

Common Sense and Casual Reasoning in LLMs

Large Language Models (LLMs) have shown state-of-the-art performance in a variety of tasks, including arithmetic and reasoning; however, to gauge the intellectual capabilities of LLMs, causal reasoning has become a reliable proxy for validating a general understanding of the mechanics and intricacies of the world similar to humans.

Social Alignment in LLMs

A small description about the things handled in Social Alignment