Publications

01
A persuasive Bengali prompt using a logical-appeal framing, and the unsafe model reply it elicits.

IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks

Saikat Mondal, Mamta, Deeksha Varshney, Oana Cocarascu, Asif Ekbal

The 2026 Conference on Empirical Methods in Natural Language Processing — EMNLP 2026 (2026)

Paper Code
02

Multi-Channel Stacked TextCNN for Biomedical Multilabel Classification

International Conference on FOSS Approaches towards Computational Intelligence and Language Technology — FOSS-CILT 2024 (2024)