Showing cs.CLShow all
2 papers · 1 filter
cs.CL2023
Negated Complementary Commonsense using Large Language Models
Navid Rezaei, Marek Z. Reformat
Larger language models, such as GPT-3, have shown to be excellent in many tasks. However, we demonstrate that out-of-ordinary questions can throw the model off guard. This work foc…
cs.CL2023
Reinforcement Learning for Topic Models
Jeremy Costello, Marek Z. Reformat
We apply reinforcement learning techniques to topic modeling by replacing the variational autoencoder in ProdLDA with a continuous action space reinforcement learning policy. We tr…