Do Large Language Models know what humans know?

Explore this paper's citation graph

Summary

Testing the viability of the language exposure hypothesis by assessing whether models exposed to large quantities of human language display sensitivity to the implied knowledge states of characters in written passages suggests that while statistical learning from language exposure may in part explain how humans develop the ability to reason about the mental states of others, other mechanisms are also responsible.

Type
preprint
Published
2022-09-04
Cited by
145
References
80
Access
Open access

Keywords

Psychology, Cognitive psychology, Task (project management), Test (biology), Human language

References

Cited by

Related papers