Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 14 references that are in the map. First posted on arXiv 9 Mar 2026.
Builds on
8 of 14 references.
References · 8
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
- 2019CamemBERT: a Tasty French Language Modelcited by 368
- 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
- 2023An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learningcited by 25
- 2024Explanation sensitivity to the randomness of large language models: the case of journalistic text classificationcited by 3
Built on by
Not cited yet.