Saikat Mondal

PhD Scholar · IIT Jodhpur

School of Artificial Intelligence & Data Science

saikatcomsci@gmail.com LinkedIn github X Google Scholar

I am a PhD Scholar at the School of Artificial Intelligence & Data Science, IIT Jodhpur, where I work on Multilingual Large Language Model (LLM) Safety, Trustworthy AI, and Natural Language Processing. My research focuses on developing robust methodologies for evaluating and mitigating safety risks in multilingual language models, including harmful content generation, jailbreak vulnerabilities, and cross-lingual safety alignment.

My broader research interests span AI Safety, Large Language Models, Deep Learning, and Biomedical NLP, with an emphasis on building reliable and culturally aware AI systems for diverse linguistic communities. Previously, I completed my M.Tech in Data Science from Jawaharlal Nehru University and my M.Sc in Computer Science from Banaras Hindu University.

News

Aug 2026 Our paper IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks accepted to EMNLP 2026 Findings. 🎉[paper]
Jan 2025 Started my PhD at the School of Artificial Intelligence & Data Science, IIT Jodhpur.

Research Interests

Multilingual LLM SafetyTrustworthy & Responsible AINatural Language Processing (NLP)Large Language Models (LLMs)Biomedical NLPMachine Learning & Deep Learning