Research exprience

1) I am working as a PhD scholar at the Laboratory of Computational Social Systems, Indian Institute of Technology, Delhi. My primary research domain is towards building robust defence mechanisms for LLMs on generating non-toxic, unbiased, and human-aligned textual responses for hateful prompts. 

Supervisor: Prof. Tanmoy Chakraborty

Skills: Python, Pytorch, NLTK, OpenCV, Hugging Face

2) I worked closely with Dr. Anil Bandhakavi towards safe and controllable text generation from the hateful prompts and improving the trustworthiness of LLMs.