Abstract
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 clinical domains, whereas performance degrades under high semantic ambiguity. Explanatory stability directly mirrors predictive certainty, exhibiting strong convergence in univalent categories and a marked drop under diagnostic uncertainty. Furthermore, qualitative error auditing uncovers three systemic failure mechanisms: lexical hypersensitivity, semantic overlap, and loss of attribution coherence. The results support the combined use of several explanation methods and quantitative agreement metrics when auditing transformer-based models in medical text classification, and suggest prioritizing specific clinical ontologies over broad diagnostic labels.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Esteban-Herreros, J. D., Muñoz-Valero, D., Martínez-España, R., Juarez, J. M., & Moreno-Garcia, J. (2026). A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification. https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification
MLA 9
Esteban-Herreros, Javier Diaz, et al. "A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification." https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification.
Chicago (author–date)
Esteban-Herreros, Javier Diaz, David Muñoz-Valero, Raquel Martínez-España, Jose M. Juarez, and Juan Moreno-Garcia. 2026. "A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification." https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification.
Harvard
Esteban-Herreros, J. D., Muñoz-Valero, D., Martínez-España, R., Juarez, J. M. and Moreno-Garcia, J. (2026) 'A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification', Available at: https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification.
Vancouver
Esteban-Herreros JD, Muñoz-Valero D, Martínez-España R, Juarez JM, Moreno-Garcia J. A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification. https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification
IEEE
J. D. Esteban-Herreros, D. Muñoz-Valero, R. Martínez-España, J. M. Juarez, and J. Moreno-Garcia, "A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification," https://omanscience.com/en/articles/a-comparative-explainability-framework-for-deberta-v3-in-zero-shot-medical-abstract-classification.