research
∙
01/16/2023
Dissociating language and thought in large language models: a cognitive perspective
Today's large language models (LLMs) routinely generate coherent, gramma...
share
research
∙
12/19/2022
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
Language tasks involving character-level manipulations (e.g., spelling c...
research
∙
06/06/2022
What do tokens know about their characters and how do they know it?
Pre-trained language models (PLMs) that use subword tokenization schemes...
research
∙
04/17/2021
