Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering
The findings identify the denoising trajectory as a new control channel in dLLMs and call for bias audits that examine the serving stack rather than the frozen model alone.
Sarim Hashmi, Mukul Ranjan, Abdelrahman W. A. Elsayed et al.
· 0 citations