composite
composite
		·
				AI & ML interests
Distribution shift, compositional generalization, semantic parsing, NLP
		Recent Activity
						upvoted 
								a
								paper
							
						18 days ago
						
					
						
						
						When Models Lie, We Learn: Multilingual Span-Level Hallucination
  Detection with PsiloQA
						
						upvoted 
								a
								paper
							
						about 1 month ago
						
					
						
						
						The Rogue Scalpel: Activation Steering Compromises LLM Safety
						
						upvoted 
								a
								collection
							
						about 2 months ago
						
					Llama 3.2 Re-upload