Metraipolis › archive › dc_c7960547bcdb
A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification — arXiv:2610.02116
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02116
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:07:05.690Z
- SHA-256 of the archived text
6b01f5cb7f83574a783f02f3e0c9318e31f08ebb7cb104e12aeeaaca387b7e36- Stable URL of this page
https://metraipolis.com/documento/dc_c7960547bcdb
How to cite
A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification — arXiv:2610.02116 — arXiv (en), https://arxiv.org/abs/2610.02116 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7960547bcdb (Metraipolis archive dc_c7960547bcdb, sha256 6b01f5cb7f83574a783f02f3e0c9318e31f08ebb7cb104e12aeeaaca387b7e36)
BibTeX
@misc{dcc7960547bcdb,
title = {A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification — arXiv:2610.02116},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02116},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7960547bcdb; sha256 6b01f5cb7f83574a783f02f3e0c9318e31f08ebb7cb104e12aeeaaca387b7e36},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02116. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.02116 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T10:21:28.002Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).