FLAME: Factuality-Aware Alignment for Large Language Models

arXiv:2405.01525v1 Announce Type: new
Abstract: Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to enhance the factual accuracy of LLMs, and often leads to the generation of more false facts (i.e. hallucination). In this paper, we study how to make the LLM alignment process more factual, by first identifying factors that lead to hallucination in …

abstract accuracy ai assistants alignment arxiv assistants cs.ai cs.cl however language language models large language large language models leads llms natural natural language process serve standard type