Assessing mentalization in humans and large language models
Quick summary
arXiv:2608.26291v1 Announce Type: new Abstract: Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social interactions. Large language models (LLMs) demonstrate behaviour consistent with humans on theory-of-mind tasks, yet whether these models can guide adaptive behaviour through mentalization is unknown. Here we use two economic games with cognitive computational modeling to uncover the latent strategies underlying mentalization in LLMs. We tested individual LLM agents across four model families, DeepSe
Key takeaways
- arXiv:2608.26291v1 Announce Type: new Abstract: Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social interactions.
- Large language models (LLMs) demonstrate behaviour consistent with humans on theory-of-mind tasks, yet whether these models can guide adaptive behaviour through mentalization is unknown.
- Here we use two economic games with cognitive computational modeling to uncover the latent strategies underlying mentalization in LLMs.
Why it matters
“Assessing mentalization in humans and large language models” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments