Researchers showed that large language models use a small, specialized subset of parameters to perform Theory-of-Mind reasoning, despite activating their full network for every task.

A new study identifies how LLMs develop social reasoning capabilities and form theory of mind (ToM), an important discovery ...

A new study reveals that the capacity for social reasoning in large language models, a trait similar to the human “theory of mind,” originates from an exceptionally small and specialized subset of the ...

Human brains are superior to LLMs in energy efficiency, but the models can become better at using their networks ...