Uncovering Concept Drift in Transformer-Based Text Classifiers, Mariam Al-Saad, Johannes Hötte, Robert M. Clark, and Daniel G. Preston, 2023Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (Association for Computational Linguistics)DOI: 10.18653/v1/2023.eacl-main.290 - Discusses drift detection specifically in transformer-based models, including methods for analyzing changes in embedding spaces relevant to LLMs.
A Kernel Two-Sample Test, Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Schölkopf, Alexander Smola, 2012Journal of Machine Learning Research, Vol. 13 (JMLR) - Foundational paper introducing the Maximum Mean Discrepancy (MMD) test, a key statistical method for comparing distributions in high-dimensional spaces.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks, Nils Reimers and Iryna Gurevych, 2019Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (Association for Computational Linguistics)DOI: 10.18653/v1/D19-1410 - Introduced Sentence-BERT, a widely adopted model for generating high-quality sentence embeddings, relevant for embedding-based drift detection in LLMs.