139 citations · 462 across the 39 of their papers we have counts for
4 papers · 2 filters
Deep de Finetti: Recovering Topic Distributions from Large Language Models
Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers +2
Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that c…
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
R. Thomas McCoy, Shunyu Yao, Dan Friedman +2
The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding…
Modeling rapid language learning by distilling Bayesian priors into artificial neural networks
R. Thomas McCoy, Thomas L. Griffiths
Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science. Bayesian mo…
How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech
Aditya Yedetore, Tal Linzen, Robert Frank +1
When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical str…