Rima Hazra
Rima Hazra
Embedded Files
I am an Assistant Professor at the Institute for Advancing Intelligence (IAI), TCG CREST. Previously, I served as a Research Scientist and Manager in the Department of Computer Science at the National University of Singapore (NUS). Before that, I was a Postdoctoral Research Fellow at Eindhoven University of Technology (TU/e) and the Singapore University of Technology and Design (SUTD). I received my PhD from the Indian Institute of Technology Kharagpur (IIT Kharagpur), where I worked under the guidance of Prof. Animesh Mukherjee and Prof. Bibhas Adhikari, currently with Fujitsu Research, USA. During my doctoral studies, I was also a member of the Complex Network Research Group (CNeRG).
I am an Assistant Professor at the Institute for Advancing Intelligence (IAI), TCG CREST. Previously, I served as a Research Scientist and Manager in the Department of Computer Science at the National University of Singapore (NUS). Before that, I was a Postdoctoral Research Fellow at Eindhoven University of Technology (TU/e) and the Singapore University of Technology and Design (SUTD). I received my PhD from the Indian Institute of Technology Kharagpur (IIT Kharagpur), where I worked under the guidance of Prof. Animesh Mukherjee and Prof. Bibhas Adhikari, currently with Fujitsu Research, USA. During my doctoral studies, I was also a member of the Complex Network Research Group (CNeRG).
My research focuses on building reliable, safe, and responsible AI systems, with particular interests in LLM alignment, AI safety, reasoning, responsible AI, multimodal and multilingual learning, natural language processing, machine learning, and complex networks. My broader goal is to understand and develop AI systems that are not only capable, but also trustworthy, robust, and aligned with human expectations and values.
My research focuses on building reliable, safe, and responsible AI systems, with particular interests in LLM alignment, AI safety, reasoning, responsible AI, multimodal and multilingual learning, natural language processing, machine learning, and complex networks. My broader goal is to understand and develop AI systems that are not only capable, but also trustworthy, robust, and aligned with human expectations and values.
News
News
Aug'2026 -ย New paper released! ๐ Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch [PDF][Code]
Aug' 2026- 3 papers accepted at EMNLP Main and Findings 2026!ย
Jul'2026 -ย 1 paper accepted at TMLR 2026! Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations [PDF]
Feb'2026 - New paper released! From fluent to verifiable: Claim-level auditability for deep research agents [PDF]
Dec' 2025 -ย Served as chair at Pan India Forum, IndoML 2025
Dec' 2025 - Delivered half day tutorial at AACL 2025 on AI safety and alignment
Nov'2025 - ๐ AAAI 2026 acceptance! "AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models" [PDF]ย
Oct'2025 - ย ๐ TMLR acceptance! "MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation" [PDF]
Sept'2025 -ย ๐ Paper accepted at EMNLP 2025! ๐ฏ โSoteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment" [PDF]
Aug'2025 - New paper out! "AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models" [PDF]
May'2025 - New paper out! "Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations" [PDF]
May'2025 - New paper out! "MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation" [PDF]
Feb'2025 - New paper out! โSoteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment" [PDF]
Feb'2025 - ๐ฏPaper accepted at NAACL Industry Track 2025!๐ "Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance" [PDF]
Jan'2025 - ย ๐ฏPaper accepted at NAACL Main 2025!๐ "Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models" [PDF][Code]
Dec'2024 -ย ๐ Paper accepted at AAAI 2025 AI Alignment Track! ๐ฏ "SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models" [PDF]
Nov'2024 - ย ๐ Paper accepted at ICWSM 2025! ๐ฏ "How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries" [PDF]
Nov'2024 - Guest Lectures! Recently conducted two lectures on AI and Safety Alignment (as a part of NLP course) at CSE, IIT Kharagpur.
Oct'2024 -ย New paper released! ๐ "Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models" [PDF][Code]
Oct'2024 - ๐ Paper accepted at EMNLP 2024 Industry Track! ๐ฏ "Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context" [PDF]
Sept'2024 - ๐ Paper accepted at EMNLP 2024 Main! ๐ฏ "Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations" [PDF][Code]
2024 - ย New!๐ Received the prestigious PaliGemma Academic Program GCP Credit Award! ๐ค
2024 - ๐ฃRecently delivered a talk on AI and Safety at ACM Summer School on Generative AI for Text 2024. Access all the materials here.
2024 - New paper released! ๐ "Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations" [PDF][Code]
2024 - New paper released! ๐ "Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance" [PDF]
2024 - New paper released!๐ฏ "SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models" [PDF]
2024 - New!๐ Received the prestigious Microsoft Academic Partnership Grant (MAPG) 2024 in collaboration with Prof. Animesh Mukherjee from IIT Kharagpur. Our proposal is among just five selected across India! Congratulations to the team members!
2024 - Paper accepted at ECML PKDD 2024! "DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem" [PDF][Code]
2024 - Paper accepted at ACL 2024! โSowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Modelsโ [PDF]
Page updated
Google Sites
Report abuse