Somnath Banerjee
18 papers · 2013–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (25)
🧬
Topic Evolution
🤝
Dynamic Duo
(11)
🗃️
Keyword Collector
(71)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(11)
Natural Language Processing
(10)
Core AI
(9)
Machine Learning
(8)
Resources & Methods
(7)
Applications
(6)
Deep Learning
(5)
Core Methods
(5)
Application Areas
(4)
Architectures
(3)
Learning Types · Machine Learning
(3)
Learning Paradigms
(2)
Learning Types · Deep Learning
(2)
Data Science & Analytics
(1)
Interdisciplinary
(1)
Keywords
large language model
(7)
text classification
(6)
hate speech detection
(4)
safety alignment
(3)
convolutional neural network
(3)
parameter steering
(3)
multilingual nlp
(2)
model editing
(2)
cross-lingual transfer
(2)
multilingual model
(2)
language model
(2)
multimodal learning
(1)
word sense disambiguation
(1)
offensive language detection
(1)
information retrieval
(1)
text generation
(1)
sentiment analysis
(1)
token selection
(1)
question answering
(1)
logistic regression
(1)
Papers
AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
AAAI 2026
Beyond Guardrails: Advanced Safety for Large Language Models — Monolingual, Multilingual and Multimodal Frontiers
IJCNLP 2025
Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
NAACL 2025
Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models
NAACL 2025
SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
AAAI 2025
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
EMNLP 2025
Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
EMNLP 2024
InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
COLING 2024
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
EMNLP 2024
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
ACL 2024
hate-alert@DravidianLangTech-ACL2022: Ensembling Multi-Modalities for Tamil TrollMeme Classification
ACL 2022
Hate Speech and Offensive Language Detection in Bengali
AACL 2022
Multilingual Abusive Comment Detection at Scale for Indic Languages
NeurIPS 2022
IR like a SIR: Sense-enhanced Information Retrieval for Multiple Languages
EMNLP 2021
LIMSI_UPV at SemEval-2020 Task 9: Recurrent Convolutional Neural Network for Code-mixed Sentiment Analysis
SemEval 2020
JU_ETCE_17_21 at SemEval-2019 Task 6: Efficient Machine Learning and Neural Network Approaches for Identifying and Categorizing Offensive Language in Tweets
SemEval 2019
NITMZ-JU at IJCNLP-2017 Task 4: Customer Feedback Analysis
IJCNLP 2017
An Empirical Study of Combing Multiple Models in Bengali Question Classification
IJCNLP 2013