Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models
Noor Islam S. Mohammad, Uluğ Bayazıt
We identify \textbf{Harmfulness Propagation Dynamics (HPD)}: for harmful prompts, the projection of the last-token hidden state onto a learned harm direction rises monotonically wi…
cs.CL2026
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
Noor Islam S. Mohammad, Ulug Bayazit
Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no m…