Evaluation tool to assess the cultural relevance of images for user-defined culture labels
			
	
	AI & ML interests
None defined yet.
Recent Activity
	View all activity
	
				Papers
		
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language

Position: Privacy Is Not Just Memorization!
- 
	
	
	SOTOPIA-π: Interactive Learning of Socially Intelligent Language AgentsPaper • 2403.08715 • Published • 21
- 
	
	
	SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsPaper • 2310.11667 • Published • 4
- 
	
	
	cmu-lti/sotopiaUpdated • 48 • 4
- 
	
	
	cmu-lti/sotopia-piViewer • Updated • 33.4k • 166 • 8
Evaluation tool to assess the cultural relevance of images for user-defined culture labels
			
	
	- 
	
	
	SOTOPIA-π: Interactive Learning of Socially Intelligent Language AgentsPaper • 2403.08715 • Published • 21
- 
	
	
	SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsPaper • 2310.11667 • Published • 4
- 
	
	
	cmu-lti/sotopiaUpdated • 48 • 4
- 
	
	
	cmu-lti/sotopia-piViewer • Updated • 33.4k • 166 • 8
			datasets
			10
		
			
	
	
	
	
	cmu-lti/caire-specific
			Viewer
			• 
	
				Updated
					
				• 
			
			68
	
				• 
					
					9
				
				
				
cmu-lti/interactive-swe
			Viewer
			• 
	
				Updated
					
				• 
			
			500
	
				• 
					
					11
				
				
				
cmu-lti/caire-universal
			Viewer
			• 
	
				Updated
					
				• 
			
			400
	
				• 
					
					6
				
				
				
cmu-lti/caire-index-ckpts
	
				Updated
					
				
	
				• 
					
					3
				
				
				
cmu-lti/AI-LieDar
	
				Updated
					
				
	
				• 
					
					16
				
				
				
cmu-lti/agents_vs_script
			Viewer
			• 
	
				Updated
					
				• 
			
			20.3k
	
				• 
					
					35
				
				• 
					
					3
				
cmu-lti/sotopia
	
				Updated
					
				
	
				• 
					
					48
				
				• 
					
					4
				
cmu-lti/sotopia-pi
			Viewer
			• 
	
				Updated
					
				• 
			
			33.4k
	
				• 
					
					166
				
				• 
					
					8
				
cmu-lti/cobracorpus
			Viewer
			• 
	
				Updated
					
				• 
			
			32.6k
	
				• 
					
					247
				
				• 
					
					4
				
cmu-lti/multi-figqa
			Viewer
			• 
	
				Updated
					
				• 
			
			6.37k
	
				• 
					
					11
				
				
				
