PLOT：通过最优传输进行神经因果抽象的渐进定位
PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
AI总结：
PLOT通过最优传输框架实现因果变量的定位，能够在不同复杂度的实验中高效定位因果抽象，提升因果解释的效率和准确性。
摘要：
因果抽象提供了一个系统的方法来解释神经网络的机制，通过反事实干预分析将高层因果模型与神经网络的底层计算对齐。现有方法如分布式对齐搜索（DAS）学习表达性子空间干预，但相关神经位点是未知的，因此寻找处理点需要计算负担繁重的候选位点搜索。我们引入PLOT（通过最优传输进行渐进定位），一个基于传输的框架，从抽象和神经干预的输出效应几何中定位因果变量。PLOT在抽象变量和候选神经位点之间拟合最优传输耦合，产生一个全局软对应关系，可以校准为干预处理点。在简单设置中，单个耦合个体神经元即可。在较大模型中，PLOT逐步应用，从粗略位点如标记、时间步或层到更精细的支撑如坐标组或PCA跨度，可选地根据本地化信号指导DAS。在增加复杂性的实验中，仅传输的PLOT处理点异常快速且在准确性上具有竞争力，而PLOT指导的DAS在DAS级别的准确性上以远低于完整DAS运行时间达到，为大规模因果抽象研究提供高效的定位引擎。
英文摘要：
Causal abstraction offers a principled framework for mechanistic interpretability, aligning a high-level causal model with low-level neural computation through interchange intervention analysis. Finding such an alignment, however, often requires fitting and evaluating separate learned mappings across many candidate neural locations. We introduce PLOT, a gradient-free approach for joint correspondence discovery via a global matching of intervention effects. PLOT represents abstract and neural interventions by geometric signatures of their effects on the shared task output and fits an optimal transport coupling between the two collections. The coupling can be calibrated directly into an executable intervention handle or used progressively to select coarse parent sites for finer localization, reducing the cost of searching broad collections of neural sites. Experiments on hierarchical equality, binary addition, and multiple-choice question answering (MCQA) demonstrate fast and accurate direct handles without learning intervention rotations and show that progressive localization can improve accuracy under intervention-size constraints while reducing computational cost. PLOT can also guide gradient-based subspace learning, with PLOT-guided distributed alignment search (DAS) attaining accuracy comparable to full DAS at approximately $3.6\times$ and $20\times$ lower serial runtime on binary addition and MCQA, respectively. PLOT thus separates the search for candidate correspondences from optional subspace learning and provides a common framework for constructing and testing neural intervention handles for a given causal model.
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。
