PPaperPicks

Sayan Layek

8 papers at tracked venues · 2 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance
  2. How (Un)ethical Are Instruction-Centric Responses of LLMs? Unveiling the Vulnerabilities of Safety Guardrails to Harmful Queries
  3. Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
  4. SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
  5. Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
  6. Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
  7. Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
  8. Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models