A Comparative Explainability Framework for DeBERTa-v3 in Zero-Shot Medical Abstract Classification· DeBERTa-v3 零样本医学摘要分类的可解释性框架对比
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 agreemen
对比 DeBERTa-v3 在零样本医学摘要分类中的可解释性方法
- 核心方法
- 使用自然语言推理引擎在医学摘要语料库上实施零样本分类，比较五种解释方法（SHAP、LIME、遮挡、Input x Gradient 和 Attention x Gradient）
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 不同可解释性方法对同一输入和预测产生不同解释，导致解释的不一致性问题
- 关键实验
- 在 Medical Abstracts 语料库上进行实验，每类诊断有五个增强假设，每类包含一千个平衡样本
- 主要贡献
- 提出了一种标准化的顶级 token 归因方法来评估不同解释方法的一致性
- 意义与局限
- 有助于理解 DeBERTa-v3 在医学摘要分类中的预测机制，但实验规模有限可能影响泛化性