Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Understanding Confabulation and Rethinking Reconstruction in Activation Explanations
Gert Lek, Zixuan Xia, Pin-Yu Chen +1
Natural Language Autoencoders (NLAs) produce unsupervised text explanations of a model's activations: a verbalizer describes an activation and a reconstructor learns to recover it…
cs.CL2026
Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
Gert Lek, Abele Malan, Chaoyi Zhu +3
Guard models are the last line of defense between a language model and a harmful output, yet their training objective is surprisingly narrow. Existing guards learn to predict a sin…