LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language
Published in Under Review, 2025
Neeraja Kirtane*, Yubin Ge, Hao Peng, Dilek Hakkani-Tür
Download here
Published in Under Review, 2025
Neeraja Kirtane*, Yubin Ge, Hao Peng, Dilek Hakkani-Tür
Download here
Published in Under Review, 2024
Neeraja Kirtane, Deema Alnuhait, Muhammad Khalifa, Hao Peng
Download here
Published in Deployable AI workshop, AAAI, 2023
Neeraja Kirtane, Aditya Kane, V Manushree
Quantified bias in Hindi Language model- Muril.Efficiently finetuned by unfreezing less than 1 percent of the parameters. Results showed that debiasing reduced the bias.
Download here
Published in Wiki Workshop, 2023
Neeraja Kirtane, Anuraag Shankar, Chelsi Jain, Ganesh Katrapati, Senthamizhan V, Raji Baskaran, Balaraman Ravindran
Wikipedia is the most widely available structured repository of information on the Internet. However, gender disparity has been observed in wiki articles, and it is a major issue. We aim to tackle this problem using Machine Learning methods to generate wiki-like biographies for notable women on Wikipedia. We present Hidden Voices, a project which will assist wiki editors and enthusiasts in writing more biographies about women, thereby increasing their representation on Wikipedia.
Download here
Published in GCLR workshop, AAAI, 2023
Download here
Published in GeBNLP, NAACL, 2022
Download here
Published in WASSA, ACL, 2022
Aditya Kane, Shantanu Patankar, Neeraja Kirtane, Sahil Khose
Developed ensemble based solution consisting of multiple ELECTRA and BERT models. Proposed methods for synthetically generating datasets to mitigate class imbalance. Studied the behaviour of our models on various raw and synthetically generated datasets.
Download here
Published in WiNLP, EMNLP, 2021
Download here