Beyond Attention: Module-Level Refusal Directions in Mamba-Based Hybrid Language Models
Year: 2026
Type: conference-paper
Authors: Artem Kirilchuk, Valentin Malykh
Institution: ITMO University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: closed
OpenAlex ID: W7222086458
