Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

Large language models can store extensive world knowledge, often extractable through question-answering (e.g., "What is Abraham Lincoln's birthday?"). However, it's unclear whether the model answers questions based on exposure to exact/similar questions during training, or if it genuinely extracts knowledge from the source (e.g., Wikipedia biographies). In this paper, we conduct an in-depth study of this problem using a controlled set of semi-synthetic biography data. We uncover a relationship between the model's knowledge extraction ability and different diversity measures of the training data. We conduct (nearly) linear probing, revealing a strong correlation between this relationship and whether the model (nearly) linearly encodes the knowledge attributes at the hidden embedding of the entity names, or across the embeddings of other tokens in the training text