Opening the Black Box of Large Language Models: Two Views on Holistic Interpretability

arXiv:2402.10688v1 Announce Type: new
Abstract: As large language models (LLMs) grow more powerful, concerns around potential harms like toxicity, unfairness, and hallucination threaten user trust. Ensuring beneficial alignment of LLMs with human values through model alignment is thus critical yet challenging, requiring a deeper understanding of LLM behaviors and mechanisms. We propose opening the black box of LLMs through a framework of holistic interpretability encompassing complementary bottom-up and top-down perspectives. The bottom-up view, enabled by mechanistic interpretability, focuses on component …

abstract alignment arxiv black box box concerns cs.cl hallucination human interpretability language language models large language large language models llm llms through toxicity trust type understanding user trust values