Humans are endowed with a powerful capacity for both inductive and deductive logical thought: we easily form generalizations based on a few examples and draw conclusions from known premises. Humans al...

A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as _probabilistic conditioning_, but...

The cerebellum's capacity for neural computation is arguably unmatched. Yet despite evidence of cerebellar contributions to cognition, including language, its precise role remains debated. Here, we sy...

Composable inference algorithms with LLMs and programmable logic - benlipkin/decoding

Our goal is to understand the relationship between language and human thought. How does the language network in the brain interact with other systems to interpret meaning in the world? Can models...