Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models.

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schtze, Xuanjing Huang, Qi Zhang, Ngai Wong

Browse the full ACL paper archive.