Standard language model training employs gold human documents or human-h...
Neural retrieval models have superseded classic bag-of-words methods suc...
Language models (LMs) have recently been shown to generate more factual
...
In typical machine learning systems, an estimate of the probability of t...
Large language models can produce fluent dialogue but often hallucinate
...
Can machines learn to use a search engine as an interactive tool for fin...
Large pre-trained language models (LMs) are capable of not only recoveri...
While Reinforcement Learning (RL) approaches lead to significant achieve...
We investigate the use of ellipsoidal trust region constraints for
secon...
Gradient-based optimization methods are the most popular choice for find...