Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies

ArXi:2603.08241v1 Announce Type: new Transformer models are now a cornerstone in natural language processing. Yet, explaining their decisions remains a challenge. It was shown recently that the same model trained on the same data with a different randomness can lead to very different explanations. In this paper, we investigate how the (syntactic) context, the classes to be learned and the tasks influence this explanations' sensitivity to randomness.