Source-Aware Training Enables Knowledge Attribution in Language Models

arXiv:2404.01019v1 Announce Type: new
Abstract: Large language models (LLMs) learn a vast amount of knowledge during pretraining, but they are often oblivious to the source(s) of such knowledge. We investigate the problem of intrinsic source citation, where LLMs are required to cite the pretraining source supporting a generated response. Intrinsic source citation can enhance LLM transparency, interpretability, and verifiability. To give LLMs such ability, we explore source-aware training -- a post pretraining recipe that involves (i) training the LLM to …

abstract arxiv attribution cs.ai cs.cl generated intrinsic knowledge language language models large language large language models learn llms pretraining training type vast