Large language models (LLMs) outperform information retrieval techniques for downstream
knowledge-intensive tasks when being prompted to generate world knowledge. However …

Existing knowledge-grounded dialogue (KGD) systems access the knowledge from an
external knowledge base, then generate the context-coherent response accordingly …

Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the
capacity to handle knowledge-intensive NLP tasks alone; thus, several works have …

Existing knowledge-grounded conversation systems generate responses typically in a
retrieve-then-generate manner. They require a large knowledge base and a strong …

While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts
of knowledge, it remains unclear how much of this parametric knowledge is actually usable …

In human interaction, effective communication relies on shared cognitive processes that
facilitate the ability of individuals to comprehend the intended message of their interlocutors …

The inadequate awareness of real-world knowledge often causes machines to produce
generic responses, such as 'I think so.', which may bring the degression of user interests …

Generating faithful and fast responses is crucial in the knowledge-grounded dialogue.
Retrieval Augmented Generation (RAG) strategies are effective but are inference inefficient …

In the Knowledge Grounded Dialogue (KGD) generation, the explicit modeling of instance-
variety of knowledge specificity and its seamless fusion with the dialogue context remains …

Despite the striking advances in recent language generation performance, model-generated
responses have suffered from the chronic problem of hallucinations that are either untrue or …