Papers
arxiv:2605.26315

Curriculum Learning for Safety Alignment

Published on May 25
Authors:
,
,

Abstract

Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibits poor out-of-distribution (OOD) generalisation. In this paper, we investigate whether Curriculum Learning can improve the robustness of DPO-based safety alignment. We propose Staged-Competence, a curriculum-based framework that organises preference data by difficulty, employs competence-based sampling, and progressively updates the reference model during training. Averaged across three model families, Staged-Competence reduces OOD harmful response rates by 16% and jailbreak attack success rates by 20%, while preserving general capabilities with near-zero over-refusal. We further show that Staged-Competence (1) matches baseline safety with only 75% of the training data and (2) yields better separation between safe and unsafe responses. Staged-Competence is agnostic to the policy optimisation loss and can extend to other DPO variants and alignment domains. Our code and data are available at https://github.com/Sandeep5500/curriculum-learning-for-safety.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.26315
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.26315 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.26315 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.26315 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.