Anna Ivanova
Anna Ivanova
About
Position
Publications
News
Resources
Thesis
CV
Light
Dark
Automatic
3
Dissociating language and thought in large language models: a cognitive perspective
Large language models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their capabilities remain split. Here, we evaluate LLMs using a distinction between formal competence — knowledge of linguistic rules and patterns — and functional competence — understanding and using language in the world. We ground this distinction in human neuroscience, showing that these skills recruit different cognitive mechanisms. Although LLMs are close to mastering formal competence, they still fail at functional competence tasks, which often require drawing on non-linguistic capacities. In short, LLMs are good models of language but incomplete models of human thought.
Kyle Mahowald
,
Anna Ivanova
,
Idan A Blank
,
Nancy Kanwisher
,
Josh Tenenbaum
,
Evelina Fedorenko
PDF
Cite
DOI
Tweeprint
Event knowledge in language models: the gap between the impossible and the unlikely
Carina Kauf
,
Anna Ivanova
,
Giulia Rambelli
,
Emmanuele Chersoni
,
Jingyuan She
,
Zawad Chowdhury
,
Evelina Fedorenko
,
Alessandro Lenci
Cite
DOI
Tweeprint
The language network reliably 'tracks' naturalistic meaningful non-verbal stimuli
Yotaro Sueoka
,
Alexander Paunov
,
Anna Ivanova
,
Idan A Blank
,
Evelina Fedorenko
Cite
DOI
Tweeprint
No evidence for a special role of language in feature-based categorization
Yael Benn
,
Anna Ivanova
,
Oliver Clark
,
Zachary Mineroff
,
Chloe Seikus
,
Jack Santos Silva
,
Rosemary Varley
,
Evelina Fedorenko
Cite
DOI
Tweeprint
Cite
×