arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.15740cs.AI
收藏

人工智能中的命题可解释性

Propositional Interpretability in Artificial Intelligence

David J. Chalmers

AI总结:

本文主张命题可解释性在AI中的重要性,提出思维记录这一核心挑战,并评估了现有可解释性方法作为命题可解释性手段的优缺点。

摘要:

机制可解释性是一项通过内部机制解释AI系统在做什么的研究计划。我分析了该计划的某些方面,提出了一些具体挑战,并评估了迄今为止的进展。我主张命题可解释性的重要性,它涉及用命题态度来解释系统的机制和行为:对命题(例如外面很热这一命题)的态度(如信念、欲望或主观概率)。命题态度是我们解释人类的核心方式,它们在AI中可能同样处于核心地位。一个核心挑战是我所称的思维记录:创建能够随时间记录AI系统中所有相关命题态度的系统。我考察了当前流行的可解释性方法(如探测、稀疏自编码器和思维链方法)以及哲学解释方法(包括基于心理语义学的方法),以评估它们作为命题可解释性方法的优缺点。

英文摘要:

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to date. I argue for the importance of propositional interpretability, which involves interpreting a system's mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems that log all of the relevant propositional attitudes in an AI system over time. I examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including those grounded in psychosemantics) to assess their strengths and weaknesses as methods of propositional interpretability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑