Mechanistic interpretability researchers applying causality theory to LLMs
机制可解释性研究人员将因果理论应用于LLM
HN Points: 95 / 68 comments | Author: adunk | HN Discussion: item?id=48883090 | Source: cacm.acm.org
Original Article
URL Source: https://cacm.acm.org/news/can-we-understand-how-large-language-models-reason/
⋯ 继续阅读请登录会员 ⋯