Work

Does Abliteration Change the Effect of Cybersecurity Fine-Tuning?

Year: 2026
Type: preprint
Abstract: Under peer review. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Does making a language model less likely to refuse a request help it learn from cybersecurity training? We compared two versions of Qwen 3.5 4B, one original and one edited to reduce refusals, before and after the same training. On 850 cybersecurity multiple-choice questions, the original model returned 10 more correct answers after training. The edited model returned 312 fewer. The scoring rule required an answer in the requested format. Even with 16 times as much room to respond, the trained, edited model returned 614 answers without a valid choice. The study leaves open how many of those answers a human reader could interpret correctly. For practitioners evaluating a model for a security workflow, the distinction matters. A model can be willing to answer and still fail to give a tool the answer it needs. Testing the starting model and the trained one on the same questions makes that change visible. The study covers one model family and one training run per starting state.
Language: English
Open Access status: green
OpenAlex ID: W7236591848
Cites:
Cited by:
Related to: 10