Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
Lists
Only you see this
BibTeX
@inproceedings{yu2024unveiling,
author = {Zhongzhi Yu and Zheng Wang and Yonggan Fu and Huihong Shi and Khalid Shaikh and Yingyan Celine Lin},
title = {{Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration}},
booktitle = {International Conference on Machine Learning},
year = {2024},
url = {https://openreview.net/forum?id=DLTjFFiuUJ},
}