I am an Assistant Professor at the
Computer Science and Engineering Department at
IIT Hyderabad, India. I am also associated with the Department of the AI Department at
IIT Hyderabad as an affiliated faculty member. My main research areas are Natural Language Processing, Information Retrieval, and Machine Learning. We work towards advancing AI, and specifically NLP algorithms, to be robust, responsible, and respectful to a diverse audience who speak different languages and follow different cultures. We consider how NLP techniques (foundational/applied) can excel even in scenarios with limited volume of labeled data, can include desirable properties such as non-toxicity, empathy, groundedness etc. More details about our work
can be found at the website of our lab called
Natural Language and Information Processing (NLIP).
Recent News
- Maharaj and Kaustubh's work on image transcreation is ranked first in the Machine Translation for Vision Challenge at MAPS@CVPR 2026. Kaustubh is an intern working with me. Amazing, Kaustubh.
- Maharaj's work on Indic Language Tokenization is accepted at Findings of ACL 2026.
- Aishwarya's work titled "A Unified View on Emotion Representation in Large Language Models" is accepted at EACL 2026
- Pramit and Maharaj have a paper at EMNLP 2026, on Cultural adaptation an dCultural elements for Indian regions and sub-regions.
- Aishwarya's work titled "Probing the Inherent Ability of Large Language Models for Generating Empathetic Responses" is accepted at IEEE Swiss Conference on Data Science | SDS 2025. It was a great experience to present the work at SDS, an event organized in fully physical mode.
- Debolena's work on hallucinations in LVLM-based captioning for drone-captured data is accepted in WACV 2025. Congratulations, Debolena.
- Suvodip's work on titled "BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation" is accepted in SIGDIAL 2024. This is the 25th edition of the conference focused on the theme of dialog systems.