A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification
[Sztuczna inteligencja] Autorzy: Javier Diaz Esteban-Herreros, David Muñoz-Valero, Raquel Martínez-España i 2 więcej
A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification of medical abstracts. The work addresses the disagreement problem in Explainable Artificial Intelligence, where different attribution methods produce divergent explanations for the same input and prediction. A natural language inference engine is implemented over the Medical Abstracts corpus with five enriched hypotheses per diagnostic category and a balanced sample of one thousand texts per class. Five explanation methods are compared: SHAP and LIME as model-agnostic approaches, occlusion and Input x Gradient as deep-learning-specific approaches, and Attention x Gradient as a transformer-specific approach. Explanations are standardized through top-token attribution, and pairwise agreement is quantified using the Jaccard index. High predictive accuracy is achieved across well-defined c…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja