Temperature sampling is a conventional approach to diversify large langu...
Despite recent progress, it has been difficult to prevent semantic
hallu...
AI researchers have posited Dungeons and Dragons (D D) as a challenge ...
With recent improvements in natural language generation (NLG) models for...
For open-domain conversational question answering (CQA), it is important...
Knowledge-grounded dialogue systems are intended to convey information t...
Knowledge-grounded dialogue agents are systems designed to conduct a
con...
Native speakers can judge whether a sentence is an acceptable instance o...
To advance models of multimodal context, we introduce a simple yet power...
The theory of situated cognition postulates that language is inseparable...
We explore whether useful temporal neural generative models can be learn...
Learning useful information across long time lags is a critical and diff...