#semantics #naturallanguageprocessing #linguistics #deeperlearning
Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multidimensional AnalysisJonathan Bennion (The Objective AI, USA), Shaona Ghosh (Nvidia, USA), Mantek Singh (Google, USA) and Nouha Dziri (Allen Institute for AI (AI2), USA)
https://youtube.com/watch?v=mKXpwb2SSE8&ab_channel=ComputerScience%26ITConferenceProceedings
No comments:
Post a Comment