Somnath Banerjee
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
arXiv 2025
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
arXiv 2025
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
arXiv 2024
DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
arXiv 2024
SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
arXiv 2024
Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
arXiv 2024
Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages
arXiv 2022
Hate Speech and Offensive Language Detection in Bengali
arXiv 2022
Affiliations
Frequent co-authors
10from 8 papers