Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about political beliefs, social norms, religion, gender attitudes, and cultural values. This paper studies privacy-preserving alignment on questionnaire-derived data from the World Values Survey, where supervision takes the form of ordinal labels rather than standard pairwise rankings. Existing efforts mainly focus on general privacy protections upon model training, while data-specific methods for survey data remain unexplored. We first show the vulnerability of aligned models, then formulate the task as rating prediction...
| Authors | Xiuyuan Qi, Yi Wang, Wenjie Wang |
|---|---|
| Primary category | cs.CR |
| Published | 12 October 2026 |
| Last updated at source | 12 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.