BEGIN:VCALENDAR
BEGIN:VEVENT
SUMMARY:David Ifeoluwa Adelani: Scaling Multilingual Evaluation of LLMs to
  Many Languages
DTSTART:20251030T203000Z
DTEND:20251030T220000Z
UID:https://cdh.princeton.edu/events/2025/10/david-adelani/
DESCRIPTION:\n\n\n\n\n    \n        \n    \n    Watch recording:\n    \n\n
     \n\n    \n    \n    \n\n\n\n    \n\n\n\n  Free and open to the public.
 Despite the widespread adoption of Large Language Models (LLMs)\, their re
 markable capabilities remain limited to a few high-resource languages. In 
 this talk\, David Ifeoluwa Adelani will describe different approaches to s
 caling evaluation to several languages. He will describe simple strategies
  for extending multilingual evaluations by repurposing existing English da
 tasets to over 200 languages for both text (SIB-200) and speech modalities
  (Fleurs-SLU). He will also introduce IrokoBench–a human-translated benc
 hmark dataset for 17 typologically diverse low-resource African languages 
 covering three tasks: natural language inference\, mathematical reasoning\
 , and multi-choice knowledge-based question answering. The talk will concl
 ude with highlights from recent projects that make some of these challengi
 ng datasets more multicultural for visual question answering and intent de
 tection tasks\, to encourage practical usage of LLMs within the low-resour
 ce communities.Dr. David Adelani is an Assistant Professor at the McGill U
 niversity School of Computer Science\, a Core Academic Member at Mila - Qu
 ebec AI Institute\, and a Canada CIFAR AI Chair. Before his appointment at
  McGill University\, he was a postdoctoral and DeepMind fellow at Universi
 ty College London\, United Kingdom. He received his Ph.D. in Computer Scie
 nce from the Department of Language Science and Technology at Saarland Uni
 versity in Germany in 2023\, where he was awarded a Dr. Eduard-Martin Outs
 tanding Doctoral Prize. His research interests include multilingual natura
 l language processing with a focus on low-resource languages\, speech proc
 essing\, privacy\, and safety of large language models. With over 40 publi
 cations in leading NLP and Speech Processing venues like ACL\, TACL\, EMNL
 P\, NAACL\, COLING\, and Interspeech\, he has made significant contributio
 ns to NLP for low-resource languages. Notably\, one of his publications re
 ceived the Best Paper Award (Global Challenges) at COLING 2022 for develop
 ing AfroXLMR\, a multilingual pre-trained language model for African langu
 ages. Other notable awards include an Area Chair Award at IJCNLP-AACL 2023
  and an Outstanding Paper Award and Best Theme Paper Award at NAACL 2025.\
 n\n\n\n  \n    \n    Series co-sponsors and supporters\n    \n\n  \n\n\n\n
 \n    \n    \n    \n\n\n\n        \n        \n        \n            \n    
         \n                \n            \n            \n            \n    
         \n                \n            \n            \n            \n    
     \n\n        \n    \n\n\n\n\n\n  \n    \n    \n    \n      Download the
  poster for this event.\n    \n\n    \n      \n        \n          \n     
        \n\n  \n\n\n            \n              \n                AAA-David
 -Adelani-Poster\n              \n              (PNG\, 1.2 MB)\n          
   \n          \n        \n      \n    \n  \n\n\n\n\n  \n\n    \n      \n  
       \n            \n    \n    Related events\n    \n\n        \n\n      
   \n      \n    \n\n    \n\n    \n          \n          \n\n    \n        
 \n            \n                \n                    \n                  
       African Languages in the Age of AI (AAA) Speaker Series\n           
          \n                \n            \n\n            \n            \n\
 n                \n                    Bringing leading scholars to Prince
 ton to discuss the opportunities and challenges for developing technologie
 s that empower African languages\n\n                \n                \n\n
             \n        \n\n        \n\n        \n            \n            
     \n                    \n                \n            \n\n            
 \n                \n                \n                \n                \n
                 \n                \n                \n            \n      
   \n    \n\n          \n          \n\n    \n        \n            \n      
           \n                    \n                        Towards AI Model
 s That Can Visually Understand the World&#x27\;s Cultures\n               
      \n                \n            \n\n            \n            \n\n   
              \n\n                    \n                    \n             
        \n                    \n                    \n                    \
 n                    \n                        \n                         
    \n                                Nov 22 2024 4:30PM–6:00PM\n        
                     \n                        \n                    \n    
                 \n                    \n                    \n            
         \n\n                    \n                        \n              
           Graham Neubig\n                        \n                    \n\
 n                \n\n            \n        \n\n        \n            \n   
              \n                    African Languages in the Age of AI\n   
              \n            \n        \n\n        \n            \n         
        \n                    \n                \n            \n\n         
    \n                \n                \n                \n               
  \n                \n                \n                \n            \n   
      \n    \n\n          \n          \n\n    \n        \n            \n   
              \n                    \n                        End-to-End Af
 rican Language Technology\n                    \n                \n       
      \n\n            \n            \n\n                \n\n               
      \n                    \n                    \n                    \n 
                    \n                    \n                    \n         
                \n                            \n                           
      Oct 24 2024 4:30PM–6:00PM\n                            \n          
               \n                    \n                    \n              
       \n                    \n                    \n\n                    
 \n                        \n                        Ernest Mwebaze\n      
                   \n                    \n\n                \n\n          
   \n        \n\n        \n            \n                \n                
     African Languages in the Age of AI\n                \n            \n  
       \n\n        \n            \n                \n                    \n
                 \n            \n\n            \n                \n        
         \n                \n                \n                \n          
       \n                \n            \n        \n    \n\n          \n    
       \n\n    \n        \n            \n                \n                
     \n                        A New Agenda for African Languages x AI: Eve
 rything\, Everywhere\, All At Once\n                    \n                
 \n            \n\n            \n            \n\n                \n\n      
               \n                    \n                    \n              
       \n                    \n                    \n                    \n
                         \n                            \n                  
               Sep 19 2024 4:30PM–6:00PM\n                            \n 
                        \n                    \n                    \n     
                \n                    \n                    \n\n           
          \n                        \n                        Vukosi Mariva
 te\n                        \n                    \n\n                \n\n
             \n        \n\n        \n            \n                \n      
               African Languages in the Age of AI\n                \n      
       \n        \n\n        \n            \n                \n            
         \n                \n            \n\n            \n                
 \n                \n                \n                \n                \n
                 \n                \n            \n        \n    \n\n      
   \n    \n  \n\n\n\n\n\n  \n\n    \n      \n        \n            \n    \n
     Related research group\n    \n\n        \n\n        \n      \n    \n\n
     \n\n    \n          \n          \n\n    \n        \n            \n    
             \n                    \n                        African Langua
 ge Technologies Lab\n                    \n                \n            \
 n\n            \n            \n\n                \n                    A l
 ab focused on increasing the representation of African languages in NLP\, 
 LLMs\, and AI. Director: Christiane Fellbaum\n\n                \n        
         \n\n            \n        \n\n        \n\n        \n            \n
                 \n                    \n                \n            \n\n
             \n                \n                \n                \n      
           \n                \n                \n                \n        
     \n        \n    \n\n        \n    \n  \n\n\n\nhttps://cdh.princeton.ed
 u/events/2025/10/david-adelani/
LOCATION:103 Bendheim House\, 26 Prospect Ave\, Princeton\, NJ 08540
END:VEVENT
END:VCALENDAR
