方法对比

	可解释句子嵌入	可解释 Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2016–2018	2017–2021
提出者	Conneau et al.; Ribeiro et al. (probing + LIME frameworks)	Vaswani et al. (Transformer); explainability extensions by Chefer et al. and the broader XAI community
类型	Post-hoc interpretability applied to sentence encoders	Interpretable deep learning model
开创性文献	Conneau, A., Kruszewski, G., Lample, G., Barrault, L., & Baroni, M. (2018). What you can cram into a single $\vec{v}$ector: Probing sentence embeddings for linguistic properties. In Proceedings of ACL 2018, pp. 2126–2136.	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
别名	interpretable sentence representations, XAI sentence embeddings, probing sentence embeddings, explainable sentence vectors	XAI Transformer, Interpretable Transformer, Transparent Transformer, Explainable Attention Model
相关	6	4
摘要	Explainable sentence embeddings combine dense sentence representation learning with post-hoc or intrinsic interpretability tools — such as probing classifiers, LIME, SHAP, or attention attribution — to reveal what linguistic and semantic information is encoded in a sentence vector and why a downstream model makes a given prediction. The goal is to retain the representational power of modern encoders while making their behavior auditable.	An Explainable Transformer combines a standard or pre-trained Transformer architecture with post-hoc or built-in interpretability techniques — such as attention rollout, gradient-weighted attention, or SHAP — to reveal which input tokens or regions drove each prediction. The approach bridges high predictive accuracy with the transparency required in high-stakes or regulated domains.