NEWSLETTER
Does spatial cognition rise in border models?
Not yet. We present space, a reference point that systematically evaluates spatial cognition in border models. Our reference point is ...
Tag: cognition
ReliabilityBench: Measuring the unpredictable performance of large language models configured in five key domains of human cognition
The research evaluates the reliability of large language models (LLMs) such as GPT, LLaMA and BLOOM, widely used in various ...
Recommended.
