Backward Lens: Projecting Language Model Gradients into the Vocabulary Space Shahar Katz author Yonatan Belinkov author Mor Geva author Lior Wolf author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication katz-etal-2024-backward 10.18653/v1/2024.emnlp-main.142 https://aclanthology.org/2024.emnlp-main.142/ 2024-11 2390 2422