Browsing Tag
algorithm
3 posts
Data Poisoning: A Threat to AI and How to Mitigate It
Almost anyone can poison a machine learning (ML) dataset to alter its behavior and output substantially and permanently.…
A New Algorithm for Improving Safety in Language Models
A new algorithm called Prompt Automatic Iterative Refinement (PAIR) has been developed by researchers from the University of…
Improving AI Language Models’ Math Problem-solving Abilities
Researchers from Microsoft Research Asia, Peking University, and Xi’an Jiaotong University have made a groundbreaking discovery in enhancing…