Somnath Banerjee

44 papers A* 4A 1B 1Journal 27Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models. AAAI Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee, Rima Hazra, Somak Aditya, Animesh Mukherjee
2026	J	`jnl`	Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages. CoRR Somnath Banerjee, Rima Hazra, Animesh Mukherjee
2026	J	`jnl`	From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents. CoRR Razeen A Rasheed, Somnath Banerjee, Animesh Mukherjee, Rima Hazra
2026	J	`jnl`	SafeMath: Inference-time Safety improves Math Accuracy. CoRR Sagnik Basu, Subhrajit Mitra, Aman Juneja, Somnath Banerjee, Rima Hazra, Animesh Mukherjee
2026	J	`jnl`	SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems. CoRR Rima Hazra, Bikram Ghuku, Ilona Marchenko, Yaroslava Tokarieva, Sayan Layek, Somnath Banerjee, Julia Stoyanovich, Mykola Pechenizkiy
2025	J	`jnl`	AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models. CoRR Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee, Rima Hazra, Somak Aditya, Animesh Mukherjee
2025	J	`jnl`	Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations. CoRR Somnath Banerjee, Pratyush Chatterjee, Shanu Kumar, Sayan Layek, Parag Agrawal, Rima Hazra, Animesh Mukherjee
2025	—	`conf`	Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance. NAACL (Industry Track) Somnath Banerjee, Avik Halder, Rajarshi Mandal, Sayan Layek, Ian Soboroff, Rima Hazra, Animesh Mukherjee
2025	A	`conf`	How (Un)ethical Are Instruction-Centric Responses of LLMs? Unveiling the Vulnerabilities of Safety Guardrails to Harmful Queries. ICWSM Somnath Banerjee, Sayan Layek, Rima Hazra, Animesh Mukherjee
2025	J	`jnl`	MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation. CoRR Sayantan Adak, Somnath Banerjee, Rajarshi Mandal, Avik Halder, Sayan Layek, Rima Hazra, Animesh Mukherjee
2025	J	`jnl`	MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation. Trans. Mach. Learn. Res. Sayantan Adak, Somnath Banerjee, Rajarshi Mandal, Avik Halder, Sayan Layek, Rima Hazra, Animesh Mukherjee
2025	—	`conf`	Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models. NAACL (Long Papers) Somnath Banerjee, Sayan Layek, Hari Shrawgi, Rajarshi Mandal, Avik Halder, Shanu Kumar, Sagnik Basu, Parag Agrawal, Rima Hazra, Animesh Mukherjee
2025	J	`jnl`	ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models. CoRR Somnath Banerjee, Sayan Layek, Sayantan Adak, Mykola Pechenizkiy, Animesh Mukherjee, Rima Hazra
2025	A*	`conf`	SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models. AAAI Somnath Banerjee, Sayan Layek, Soham Tripathy, Shanu Kumar, Animesh Mukherjee, Rima Hazra
2025	—	`conf`	Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment. EMNLP (Findings) Somnath Banerjee, Sayan Layek, Pratyush Chatterjee, Animesh Mukherjee, Rima Hazra
2025	J	`jnl`	Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment. CoRR Somnath Banerjee, Sayan Layek, Pratyush Chatterjee, Animesh Mukherjee, Rima Hazra
2024	J	`jnl`	Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance. CoRR Somnath Banerjee, Avik Halder, Rajarshi Mandal, Sayan Layek, Ian Soboroff, Rima Hazra, Animesh Mukherjee
2024	—	`conf`	Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context. EMNLP (Industry Track) Somnath Banerjee, Amruit Sahoo, Sayan Layek, Avik Dutta, Rima Hazra, Animesh Mukherjee
2024	J	`jnl`	Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context. CoRR Somnath Banerjee, Amruit Sahoo, Sayan Layek, Avik Dutta, Rima Hazra, Animesh Mukherjee
2024	—	`conf`	DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem. ECML/PKDD (10) Somnath Banerjee, Avik Dutta, Aaditya Agrawal, Rima Hazra, Animesh Mukherjee
2024	J	`jnl`	DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem. CoRR Somnath Banerjee, Avik Dutta, Aaditya Agrawal, Rima Hazra, Animesh Mukherjee
2024	J	`jnl`	How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries. CoRR Somnath Banerjee, Sayan Layek, Rima Hazra, Animesh Mukherjee
2024	—	`conf`	InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks. LREC/COLING Somnath Banerjee, Maulindu Sarkar, Punyajoy Saha, Binny Mathew, Animesh Mukherjee
2024	J	`jnl`	InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks. CoRR Somnath Banerjee, Maulindu Sarkar, Punyajoy Saha, Binny Mathew, Animesh Mukherjee
2024	J	`jnl`	Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models. CoRR Somnath Banerjee, Sayan Layek, Hari Shrawgi, Rajarshi Mandal, Avik Halder, Shanu Kumar, Sagnik Basu, Parag Agrawal, Rima Hazra, Animesh Mukherjee
2024	J	`jnl`	SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models. CoRR Somnath Banerjee, Soham Tripathy, Sayan Layek, Shanu Kumar, Animesh Mukherjee, Rima Hazra
2024	A*	`conf`	Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations. EMNLP Rima Hazra, Sayan Layek, Somnath Banerjee, Soujanya Poria
2024	J	`jnl`	Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations. CoRR Rima Hazra, Sayan Layek, Somnath Banerjee, Soujanya Poria
2024	—	`conf`	Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models. ACL (Findings) Rima Hazra, Sayan Layek, Somnath Banerjee, Soujanya Poria
2024	J	`jnl`	Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models. CoRR Rima Hazra, Sayan Layek, Somnath Banerjee, Soujanya Poria
2023	B	`conf`	Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities. ASONAM Rima Hazra, Debanjan Saha, Amruit Sahoo, Somnath Banerjee, Animesh Mukherjee
2023	J	`jnl`	Duplicate Question Retrieval and Confirmation Time Prediction in Software Communities. CoRR Rima Hazra, Debanjan Saha, Amruit Sahoo, Somnath Banerjee, Animesh Mukherjee
2023	J	`jnl`	Evaluating the Ebb and Flow: An In-depth Analysis of Question-Answering Trends across Diverse Platforms. CoRR Rima Hazra, Agnik Saha, Somnath Banerjee, Animesh Mukherjee
2023	J	`jnl`	Redefining Developer Assistance: Through Large Language Models in Software Ecosystem. CoRR Somnath Banerjee, Avik Dutta, Sayan Layek, Amruit Sahoo, Sam Conrad Joyce, Rima Hazra
2022	—	`conf`	Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages. HT Mithun Das, Somnath Banerjee, Animesh Mukherjee
2022	J	`jnl`	Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages. CoRR Mithun Das, Somnath Banerjee, Animesh Mukherjee
2022	—	`conf`	Hate Speech and Offensive Language Detection in Bengali. AACL/IJCNLP (1) Mithun Das, Somnath Banerjee, Punyajoy Saha, Animesh Mukherjee
2022	J	`jnl`	Hate Speech and Offensive Language Detection in Bengali. CoRR Mithun Das, Somnath Banerjee, Punyajoy Saha, Animesh Mukherjee
2022	A*	`conf`	Multilingual Abusive Comment Detection at Scale for Indic Languages. NeurIPS Vikram Gupta, Sumegh Roychowdhury, Mithun Das, Somnath Banerjee, Punyajoy Saha, Binny Mathew, Hastagiri Prakash Vanchinathan, Animesh Mukherjee
2022	J	`jnl`	hate-alert@DravidianLangTech-ACL2022: Ensembling Multi-Modalities for Tamil TrollMeme Classification. CoRR Mithun Das, Somnath Banerjee, Animesh Mukherjee
2021	—	`conf`	Abusive and Threatening Language Detection in Urdu using Boosting Based and BERT Based Models: A Comparative Approach. FIRE (Working Notes) Mithun Das, Somnath Banerjee, Punyajoy Saha
2021	J	`jnl`	Abusive and Threatening Language Detection in Urdu using Boosting based and BERT based models: A Comparative Approach. CoRR Mithun Das, Somnath Banerjee, Punyajoy Saha
2021	—	`conf`	Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languages. FIRE (Working Notes) Somnath Banerjee, Maulindu Sarkar, Nancy Agrawal, Punyajoy Saha, Mithun Das
2021	J	`jnl`	Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languages. CoRR Somnath Banerjee, Maulindu Sarkar, Nancy Agrawal, Punyajoy Saha, Mithun Das