Cognitive Capability
Cognitive capability research investigates the nature and extent of thinking abilities, focusing currently on evaluating large language models (LLMs) against human benchmarks. This involves developing and applying cognitive tests, often inspired by developmental psychology, to assess LLMs' performance across various domains like reasoning, language understanding, and theory of mind. The findings are informing our understanding of both artificial and human intelligence, with implications for improving AI systems and refining cognitive science theories.
Papers
Joint Audio and Speech Understanding
Yuan Gong, Alexander H. Liu, Hongyin Luo, Leonid Karlinsky, James Glass
Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Ida Momennejad, Hosein Hasanbeig, Felipe Vieira, Hiteshi Sharma, Robert Osazuwa Ness, Nebojsa Jojic, Hamid Palangi, Jonathan Larson