Timothee Mickus, Raúl Vázquez. Why Bother with Geometry? On the Relevance of Linear Decompositions of Transformer Embeddings. In Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi, editors, Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2023, Singapore, December 7, 2023. pages 127-141, Association for Computational Linguistics, 2023. [doi]
Abstract is missing.