@article{forgettingtransformersoftmaxattentionwit, title = {Forgetting Transformer: Softmax Attention with a Forget Gate}, author = {Zhixuan Lin and Evgenii Nikishin and Xu Owen He and Aaron Courville}, year = {2025}, eprint = {2503.02130}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.02130v2}, }