Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

arXiv:2608.25735 · cs.CR, cs.AI, cs.IR, cs.LG · Submitted 2026-08-26 · Read on arXiv

cs.CR, cs.AI, cs.IR, cs.LG

Submitted: 2026-08-26

Updated: 2026-10-03

Code: https://github.com/myl7/p2rag

Terminology

• RAG — 39× in this paper · explained in 3 episodes
• Embeddings — 28× in this paper · explained in 2 episodes
• Calibration — 13× in this paper · explained in 7 episodes
• Differential Privacy — 12× in this paper · explained in 4 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Verifier — 10× in this paper · explained in 2 episodes
• Quantization — 8× in this paper · explained in 12 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Natural Questions — 5× in this paper
• Retrieval-Augmented Generation — 5× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Distillation — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 3× in this paper
• Tokenization — 3× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Differentially Private — 2× in this paper · explained in 3 episodes
• EMMA — 2× in this paper · explained in 2 episodes
• Hamming Distance — 2× in this paper · explained in 2 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Differential Privacy (DP) — 1× in this paper · explained in 7 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• National Institute of Standards and Technology — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Wally: Batched Private Nearest Neighbor Search at Scale
• MESS: Fast and Private Semantic Search on Multi-Graph HNSW
• CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
• The Llama 3 Herd of Models
• P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval
• Differentially Private Retrieval-Augmented Generation
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Qwen3 Technical Report

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs