research
∙
11/10/2022
The CRINGE Loss: Learning what language not to model
Standard language model training employs gold human documents or human-h...
share
research
∙
10/21/2022
Decoding a Neural Retriever's Latent Space for Query Suggestion
Neural retrieval models have superseded classic bag-of-words methods suc...
research
∙
03/24/2022
Language Models that Seek for Knowledge: Modular Search Generation for Dialogue and Prompt Completion
Language models (LMs) have recently been shown to generate more factual ...
research
∙
03/20/2022
Calibration of Machine Reading Systems at Scale
In typical machine learning systems, an estimate of the probability of t...
research
∙
11/09/2021
Reason first, then respond: Modular Generation for Knowledge-infused Dialogue
Large language models can produce fluent dialogue but often hallucinate ...
research
∙
09/01/2021
Boosting Search Engines with Interactive Agents
Can machines learn to use a search engine as an interactive tool for fin...
research
∙
08/04/2021
How to Query Language Models?
Large pre-trained language models (LMs) are capable of not only recoveri...
research
∙
09/04/2019
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games
While Reinforcement Learning (RL) approaches lead to significant achieve...
research
∙
05/22/2019
Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training
We investigate the use of ellipsoidal trust region constraints for secon...
research
∙
05/15/2018