The explanations of large language models have recently been shown to be sensitive to the randomness used for their training, creating a need to characterize this sensitivity. In this paper, we propose a characterization that questions the possibility to provide simple and informative explanations for such models. To this end, we give statistical definitions for the explanations' signal, noise and signal-to-noise ratio. We highlight that, in a typical case study where word-level univariate explanations are analyzed with first-order statistical tools, the explanations of simple feature-based models carry more signal and less noise than those of transformer ones. We then discuss the possibility to improve these results with alternative definitions of signal and noise that would capture more complex explanations and analysis methods, while also questioning the tradeoff with their plausibility for readers.

翻译：大型语言模型的解释近年被证明对其训练所用的随机性敏感，因此需要刻画这种敏感性。本文提出一种刻画方法，对为此类模型提供简单且信息量丰富的解释的可能性提出质疑。为此，我们给出解释信号、噪声及信噪比的统计定义。我们发现，在典型的案例分析中，当使用一阶统计工具分析词级单变量解释时，基于特征的简单模型的解释比基于Transformer的模型携带更多信号且噪声更少。随后，我们探讨了通过采用信号与噪声的替代定义（可捕捉更复杂的解释与分析方法）来改进这些结果的可能性，同时质疑了这些改进与读者理解的解释合理性之间的权衡。