Rima Hazra

Venues

Frequent coauthors

Papers

1. AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
   AAAI 2026 ·

   Sayantan Adak

   DBLP profile ↗ORCID search ↗
2. Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
   NAACL 2025 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
3. How (Un)ethical Are Instruction-Centric Responses of LLMs? Unveiling the Vulnerabilities of Safety Guardrails to Harmful Queries
   ICWSM 2025 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
4. Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
   NAACL 2025 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
5. SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
   AAAI 2025 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
6. Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
   EMNLP 2025 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
7. Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions
   EMNLP 2025 ·

   Rachneet Singh Sachdeva

   DBLP profile ↗ORCID search ↗
8. Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
   EMNLP 2024 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
9. DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
   ECML-PKDD 2024 ·

   Somnath Banerjee

   DBLP profile ↗ORCID search ↗
10. Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
    EMNLP 2024 · Rima Hazra
11. Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
    ACL 2024 · Rima Hazra