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

Romain Loncour, Jérémie Bogaert, François-Xavier Standaert
3/9/2026
cs.CL

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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. We show that they all have statistically significant impact: smallest for the (syntactic) context, medium for the classes and largest for the tasks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{loncour2026sensivity,
  title  = {Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies},
  author = {Romain Loncour and Jérémie Bogaert and François-Xavier Standaert},
  year   = {2026},
  eprint = {2603.08241},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.08241v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.08241.svg)](https://codeofpaper.com/paper/2603.08241)

Discussion