Sean Xie, Soroush Vosoughi, Saeed Hassanpour. Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 3964-3979, Association for Computational Linguistics, 2023. [doi]
Abstract is missing.