寻找合适的中介变量：从因果中介分析视角审视机制可解释性
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
AI总结：
针对可解释性领域缺乏统一理论基础、机制因果单元定义不明的问题，本文从因果中介分析视角出发，按中介变量类型和搜索方法梳理领域现状与优缺点，提出该框架可增强研究连贯性并给出未来研究建议。
摘要：
可解释性为理解神经网络以特定方式运行的方式与原因提供了一套工具。然而，该领域缺乏统一性：大多数研究采用临时评估方法，且没有共同的理论基础，这使得衡量进展以及比较不同技术的优缺点变得困难。此外，尽管机制理解被频繁讨论，但这些机制背后的基本因果单元往往没有得到明确定义。在本文中，我们提出了一种基于因果中介分析的可解释性研究视角。具体而言，我们按照所采用的因果单元（中介变量）类型以及中介变量搜索方法，对可解释性的发展历史与当前研究现状进行了分类描述。我们讨论了各类中介变量的优缺点，为特定类型的中介变量和搜索方法最适用的场景提供了见解。我们认为，这一框架能够让该领域的研究脉络更具连贯性，并帮助研究人员根据自身研究目标选择合适的方法。我们的分析为未来工作提供了可落地的建议，包括发现新的中介变量，以及开发适配这些目标的标准化评估方法。
英文摘要：
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making it difficult to measure progress and compare the pros and cons of different techniques. Furthermore, while mechanistic understanding is frequently discussed, the basic causal units underlying these mechanisms are often not explicitly defined. In this article, we propose a perspective on interpretability research grounded in causal mediation analysis. Specifically, we describe the history and current state of interpretability taxonomized according to the types of causal units (mediators) employed, as well as methods used to search over mediators. We discuss the pros and cons of each mediator, providing insights as to when particular kinds of mediators and search methods are most appropriate. We argue that this framing yields a more cohesive narrative of the field and helps researchers select appropriate methods based on their research objective. Our analysis yields actionable recommendations for future work, including the discovery of new mediators and the development of standardized evaluations tailored to these goals.
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。
