A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation

arXiv:2404.03491v1 Announce Type: new
Abstract: Empowered by the large-scale pretrained language models, existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations. However, they are still plagued by the hallucination problem, causing unpredictable factual errors in the generated responses. Recently, knowledge-grounded dialogue generation models, that intentionally invoke external knowledge resources to more informative responses, are also proven to be effective in reducing hallucination. Following the idea of getting high-quality knowledge, a few efforts have achieved pretty good performance …

abstract arxiv conversations cs.ai cs.cl dialogue errors generated hallucination however invoke knowledge language language models look natural performance responses scale systems type