DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens.

Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng

Browse the full ACL paper archive.