@inproceedings{cheng-etal-2026-drives, title = "What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal", author = "Cheng, Stephen S and Wiegreffe, Sarah and Manocha, Dinesh", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.79/", pages = "1813--1843", ISBN = "979-8-89176-459-0" }