Research

Paper

AI LLM March 09, 2026

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

Authors

Romain Loncour, Jérémie Bogaert, François-Xavier Standaert

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.

Metadata

arXiv ID: 2603.08241
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08241v1</id>\n    <title>Sensivity of LLMs' Explanations to the Training Randomness:Context, Class &amp; Task Dependencies</title>\n    <updated>2026-03-09T11:14:37Z</updated>\n    <link href='https://arxiv.org/abs/2603.08241v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08241v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-09T11:14:37Z</published>\n    <arxiv:comment>6 pages, 6 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Romain Loncour</name>\n    </author>\n    <author>\n      <name>Jérémie Bogaert</name>\n    </author>\n    <author>\n      <name>François-Xavier Standaert</name>\n    </author>\n  </entry>"
}