Studying Large Language Model Behaviors Under Realistic Knowledge Conflicts

arXiv:2404.16032v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the model's knowledge can be updated from documents provided in context. This leads to cases of conflict between the model's parametric knowledge and the contextual information, where the model may not always update its knowledge. Previous work studied knowledge conflicts by creating synthetic documents that contradict the model's correct parametric answers. We present …

arxiv cs.lg knowledge language language model large language large language model studying type