消除神经网络解释中的虚假相关性
Removing Spurious Correlation from Neural Network Interpretations
AI总结：
针对神经元解释易受对话主题等混杂因素影响的问题，提出控制主题效应的因果中介方法，并在两个大语言模型上证明调整后毒性更不局部化。
摘要：
现有用于识别导致不良和有害行为的神经元的算法，未考虑对话主题等混杂因素的影响。在本研究中，我们证明混杂因素会产生虚假相关性，并提出一种新的因果中介方法，用于控制主题的影响。在使用两个大型语言模型进行的实验中，我们研究了定位假设，并表明在调整对话主题的影响后，毒性变得不那么局部化。
英文摘要：
The existing algorithms for identification of neurons responsible for undesired and harmful behaviors do not consider the effects of confounders such as topic of the conversation. In this work, we show that confounders can create spurious correlations and propose a new causal mediation approach that controls the impact of the topic. In experiments with two large language models, we study the localization hypothesis and show that adjusting for the effect of conversation topic, toxicity becomes less localized.
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。
