Grounding dialogue response generation on external knowledge is proposed...
Instruction-tuned large language models (LLMs) have shown remarkable
gen...
Conversational models that are generative and open-domain are particular...
This paper proposes a framework for quantitatively evaluating interactiv...
Generating a short story out of an image is arduous. Unlike image captio...
Task-adaptive pre-training (TAPT) alleviates the lack of labelled data a...