PrivCode++ introduces the first DP code generation method protecting both prompts and code via latent-conditioned two-stage training, claiming higher utility and stronger privacy than prior baselines.
Privacy-preserving instructions for aligning large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
InvisibleInk achieves high-utility differentially private long-form LLM text generation at 4-8x the cost of non-private generation by isolating and clipping sensitive logits and sampling from a small superset of top-k private tokens without privacy cost.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.
citing papers explorer
-
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
PrivCode++ introduces the first DP code generation method protecting both prompts and code via latent-conditioned two-stage training, claiming higher utility and stronger privacy than prior baselines.
-
InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
InvisibleInk achieves high-utility differentially private long-form LLM text generation at 4-8x the cost of non-private generation by isolating and clipping sensitive logits and sampling from a small superset of top-k private tokens without privacy cost.
-
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
-
Small Language Models are the Future of Agentic AI
Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.