@article{efficientlongrangelanguagemodelingwith, title = {Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling}, author = {Xiang Hu and Zhihao Teng and Jun Zhao and Wei Wu and Kewei Tu}, year = {2024}, eprint = {2410.01651}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.01651v2}, }