Scholar
Rima Hazra
Google Scholar ID: QY1Ijf4AAAAJ
Research Fellow-I, SUTD, Singapore
Citations & Impact
Citations
129
H-index
6
i10-index
4
Publications
20
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- October 2025 - Paper 'MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation' accepted by TMLR; September 2025 - Paper 'Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment' accepted by EMNLP 2025; August 2025 - Released paper 'AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models'; May 2025 - Released papers 'Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations' and 'MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation'; February 2025 - Papers 'Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment' and 'Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance' accepted by NAACL Industry Track 2025, and 'Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models' accepted by NAACL Main 2025; December 2024 - Paper 'SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models' accepted by AAAI 2025 AI Alignment Track; November 2024 - Paper 'How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries' accepted by ICWSM 2025; October 2024 - Released paper 'Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models', and 'Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context' accepted by EMNLP 2024 Industry Track; September 2024 - Paper 'Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations' accepted by EMNLP 2024 Main; 2024 - Received the PaliGemma Academic Program GCP Credit Award, and the Microsoft Academic Partnership Grant (MAPG) 2024 in collaboration with Prof. Animesh Mukherjee from IIT Kharagpur, one of only five selected across India.
Research Experience
- Worked as a postdoctoral research fellow at Singapore University of Technology and Design; currently a senior postdoc at Eindhoven University of Technology.
Education
- Previously a postdoctoral research fellow at Singapore University of Technology and Design. Obtained PhD from Indian Institute of Technology, Kharagpur, under the guidance of Prof. Animesh Mukherjee and Prof. Bibhas Adhikari (currently at Fujitsu Research, US). Was a member of the Complex Network Research Group (CNeRG).
Background
- Currently a senior postdoc at the Department of Mathematics and Computer Science, Eindhoven University of Technology (TU/e). Research interests include LLM alignment, responsible AI, LLM safety and reasoning, multimodality & multilinguality, NLP, ML, and complex networks.
Miscellany
- Conducted guest lectures on AI and Safety Alignment as part of an NLP course at CSE, IIT Kharagpur in November 2024; Delivered a talk on AI and Safety at the ACM Summer School on Generative AI for Text 2024; Collaborated with Prof. Animesh Mukherjee from IIT Kharagpur to receive the prestigious Microsoft Academic Partnership Grant (MAPG) 2024, with the proposal being one of just five selected across India.
