Differential Privacy Protected Preference Alignment on Survey Derived Data

Abstract: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 and introduce label differential privacy. Building on this formulation, we construct a differential private pipeline utilizing three privacy mechanisms: randomized response, exponential mechanism, and DP-SGD. Experiments show that simple label-level mechanisms outperform gradient-level methods, and proper aggregation function for preprocessing also make large contribution. The new fine-grained private comparison motivates explorations toward language model alignment with formal privacy guarantees.

Cryptography and Security (cs.CR); Computation and Language (cs.CL); Machine Learning (cs.LG)

arXiv:2610.16458 [cs.CR]

(or arXiv:2610.16458v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2610.16458 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.