A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia

arXiv:2312.02073v2 Announce Type: replace
Abstract: Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling. Favoring the contextual information is critical for retrieval-augmented generation methods, which enrich the context with up-to-date information, hoping that grounding can rectify outdated or noisy stored knowledge. We present a …

abstract arxiv context cs.cl glitch information knowledge language language model language models large language large language models llms matrix novel parameters the matrix type