← Search

Eghbal A. Hosseini

1 accepted papers

2023

Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.

NeurIPS 2023poster

Predicting upcoming events is critical to our ability to effectively interact with our environment and conspecifics. In natural language processing, transformer models, which are trained on next-word prediction, appear to construct a general-purpose representation of language that can support divers…

Cited by 6SourcePDFScholar