2 papers
cs.CL2026
CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Philipp E. Glass, Alina Miron
Studying how fine-tuning shapes refusal and noncompliance behaviour requires knowing which training examples refuse or otherwise fail to fulfil the request. Existing annotations co…
cs.CL2026
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Philipp E. Glass, Allan Tucker, Yongmin Li +1
Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way to encode alignment prior to…