2 papers
cs.LG2026
Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate
Yoshihiro Izawa, Gouki Minegishi, Yoko Yamakata
Can LLMs recognize degradation in their own computational substrate? Inspired by anosognosia, a neurological condition in which patients fail to recognize impairments in their own…
cs.CL2026
Steering at the Source: Style Modulation Heads for Robust Persona Control
Yoshihiro Izawa, Gouki Minegishi, Koshi Eguchi +2
Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g.…