Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change in models' output logits or behaviors. While this yields more faithful evidence than correlational methods, counterfactuals nonetheless have key problems that bias our findings in specific and predictable ways. Specifically, (i) counterfactual theories do not effectively capture multiple independently sufficient causes of the same effect, which leads us to miss certain causes entirely; and (ii) counterfactual dependencies in neural networks are generally not transitive, which complicates methods for extracting and interpreting causal graphs from neural networks. We discuss the implications of these challenges for interpretability researchers and propose concrete suggestions for future work.

翻译：可解释性研究普遍默认采用反事实因果理论。多数因果方法依赖于对输入或特定模型组件激活进行反事实干预，继而观察模型输出逻辑值或行为的变化。虽然这种方法比相关性方法提供更可靠的证据，但反事实推理仍存在关键缺陷，会以特定且可预测的方式使研究结果产生偏差。具体而言：(i) 反事实理论无法有效捕捉同一效应的多个独立充分成因，导致我们完全忽略某些成因；(ii) 神经网络中的反事实依赖关系通常不具备传递性，这使从神经网络中提取和解释因果图的方法变得复杂。我们讨论了这些挑战对可解释性研究者的启示，并为未来工作提出了具体建议。