Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
Privately aligning language models with reinforcement learning.arXiv preprint arXiv:2310.16960, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2representative citing papers
A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.
citing papers explorer
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
-
Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.