Cat-DPO: Category-Adaptive Safety Alignment

April 19, 2026 ยท Grace Period ยท + Add venue

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Kaize Ding, Yue Zhao arXiv ID 2604.17299 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 0
Abstract
Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most preference-based safety alignment methods collapse safety into a single scalar that is applied uniformly to every preference pair. The result is a model that looks safe on average but stays relatively unsafe on a minority of harm categories. We cast safety alignment as a per-category constrained optimization problem and derive Cat-DPO, a direct-preference-optimization algorithm with a separate adaptive safety margin for each harm category. The margin tightens when the model still produces unsafe responses on a category and relaxes once the model catches up, so the training signal tracks each category's current difficulty rather than averaging under one global rate. Across two LLM backbones and six preference-learning baselines, Cat-DPO iimproves aggregate helpfulness and harmlessness and compresses per-category safety variance and the best-to-worst gap, offering a drop-in per-category refinement of direct preference safety alignment.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 9 years ago