Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.02859 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910928436461568 |
|---|---|
| author | Bokstaller, Jonas Altheimer, Julia Dormehl, Julian Buss, Alina Wiltfang, Jasper Schneider, Johannes Röglinger, Maximilian |
| author_facet | Bokstaller, Jonas Altheimer, Julia Dormehl, Julian Buss, Alina Wiltfang, Jasper Schneider, Johannes Röglinger, Maximilian |
| contents | Across various sectors applications of eXplainableAI (XAI) gained momentum as the increasing black-boxedness of prevailing Machine Learning (ML) models became apparent. In parallel, Large Language Models (LLMs) significantly developed in their abilities to understand human language and complex patterns. By combining both, this paper presents a novel reference architecture for the interpretation of XAI through an interactive chatbot powered by a fine-tuned LLM. We instantiate the reference architecture in the context of State-of-Health (SoH) prediction for batteries and validate its design in multiple evaluation and demonstration rounds. The evaluation indicates that the implemented prototype enhances the human interpretability of ML, especially for users with less experience with XAI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02859 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing ML Model Interpretability: Leveraging Fine-Tuned Large Language Models for Better Understanding of AI Bokstaller, Jonas Altheimer, Julia Dormehl, Julian Buss, Alina Wiltfang, Jasper Schneider, Johannes Röglinger, Maximilian Computation and Language Artificial Intelligence Across various sectors applications of eXplainableAI (XAI) gained momentum as the increasing black-boxedness of prevailing Machine Learning (ML) models became apparent. In parallel, Large Language Models (LLMs) significantly developed in their abilities to understand human language and complex patterns. By combining both, this paper presents a novel reference architecture for the interpretation of XAI through an interactive chatbot powered by a fine-tuned LLM. We instantiate the reference architecture in the context of State-of-Health (SoH) prediction for batteries and validate its design in multiple evaluation and demonstration rounds. The evaluation indicates that the implemented prototype enhances the human interpretability of ML, especially for users with less experience with XAI. |
| title | Enhancing ML Model Interpretability: Leveraging Fine-Tuned Large Language Models for Better Understanding of AI |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.02859 |