A team of engineers, mathematicians and cognitive computer scientists led by the University of Cambridge has developed an open-source evaluation platform called “ChekMate”.
This platform, powered by artificial intelligence, allows users to interact with large language models (LLMs) and evaluate their performance.
The research group studied how much LLMs help in solving problems, as well as which chatbots most users use for their intended purposes and the relationship between them.
Although the team tested “ChekMate” on mathematical problems, they noted that this platform can be adapted for a wide range of applications.
Prepared by Saidova Bahora.
