Paper
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
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
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 & 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>"
}