方法对比

	可解释的BERT分类	基于RoBERTa的分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019–2020	2019
提出者	Devlin et al. (BERT); explainability methods by Lundberg & Lee (SHAP), Ribeiro et al. (LIME), Sundararajan et al. (Integrated Gradients)	Liu, Y. et al. (Facebook AI Research / University of Washington)
类型	Pre-trained transformer classifier with post-hoc or intrinsic explainability	Pre-trained transformer fine-tuned for sequence classification
开创性文献	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186.	Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692.
别名	XAI-BERT, interpretable BERT classifier, BERT with post-hoc explanation, transparent BERT classification	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification
相关	6	5
摘要	Explainable BERT-based Classification combines the predictive power of fine-tuned BERT transformers for text classification with post-hoc or intrinsic explainability techniques — such as SHAP, LIME, attention analysis, or integrated gradients — to reveal which words or tokens drove each prediction. The result is a classifier that is both accurate and interpretable enough for high-stakes or auditable NLP applications.	RoBERTa-based Classification applies the RoBERTa pre-trained transformer — trained more robustly than BERT with dynamic masking and larger batches — to text categorisation tasks by adding a lightweight classification head on top of the [CLS] token representation and fine-tuning the entire model on labelled examples. It consistently matches or outperforms BERT on standard NLP benchmarks.