NLP

Analyzing the Robustness and the Reliability of Large Language Models

Group project for NLP701. I was responsible for handling the robustness analysis, where the SOTA LLMs were evaluated for their hallucinations.

EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation

Developed an ensemble based approach for euphemism detection, which ranked first in the Euphemism Detection Shared Task at EMNLP 2022 Workshop on Figurative Language.

Is this URL Safe: Detection of Malicious URLs Using Global Vector for Word Representation

Machine Learning models were developed and trained to classify and detect malicious URLs.

Word Galaxy Network

Network of Similar words clustered together in Vitiligo Abstracts Dataset.