MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
Paper • 2502.11246 • Published • 1
RIMA HAZRA
rimahazra
·
AI & ML interests
AI and Safety, AI Hallucinations, Natural Language Processing, Information Retrieval, Large Language Models.
Organizations
authored a
paper about 1 year ago
authored 3
papers over 1 year ago
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
Paper • 2502.11244 • Published
Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions
Paper • 2501.01872 • Published • 2
Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
Paper • 2410.12880 • Published • 3
authored 3
papers about 2 years ago
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
Paper • 2406.11139 • Published • 13
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
Paper • 2406.11801 • Published • 16
SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
Paper • 2406.12274 • Published • 16
authored 6
papers over 2 years ago
How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
Paper • 2402.15302 • Published • 4
Is this bug severe? A text-cum-graph based model for bug severity prediction
Paper • 2207.00623 • Published
DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
Paper • 2402.16159 • Published • 2
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
Paper • 2401.10647 • Published • 4
Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
Paper • 2401.12671 • Published • 2
Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities
Paper • 2309.05035 • Published • 2