mlsanityData to 7 Oct 2026

Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs

arXiv 2605.05459 ↗First posted 6 May 2026cs.CR cs.LGcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

This work introduces PAS -- Privacy Anchor Substitution, a structured mechanism for enabling user location privacy in spatial retrieval-augmented generation (RAG) systems. Unlike conventional differential privacy methods that directly perturb user locations, PAS represents location with relative anchor encoding consisting of an anchor, direction bin, and distance bin, allowing seamless integration with modern RAG pipelines. We evaluate PAS on a synthetic urban dataset and show that it achieves impressive coarse privacy guarantees, with approximately 370-400m adversarial location error, while retaining more than half of the baseline retrieval performance. Despite the slight drop in retrieval performance, the downstream generation quality under PAS remains comparatively robust, indicating that large language models can compensate for imperfect spatial retrieval. Furthermore, we provide empirical analysis showing that PAS exhibits non-monotonic privacy-utility relationship with respect to privacy parameters. We attribute this to geometric bias induced by anchor discretization, making it different from continuous noise mechanisms such as geo-indistinguishability. Our results show that structured spatial representations offer a practical approach to privacy in location based reasoning in RAG systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 54 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

34 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data20 Jun
  2. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 32

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2025Gemma 3 Technical Reportcited by 1,686
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
20 more
  1. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  2. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  4. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  6. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  7. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  8. 2013A Theoretical Analysis of NDCG Type Ranking Measurescited by 119
  9. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 48
  10. 2024RAGEval: Scenario Specific RAG Evaluation Dataset Generation Frameworkcited by 39
  11. 2024On the Privacy Risk of In-context Learningcited by 31
  12. 2025Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agentscited by 26
  13. 2024Privacy Preserving Prompt Engineering: A Surveycited by 24
  14. 2025TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planningcited by 12
  15. 2024DP-TabICL: In-Context Learning with Differentially Private Tabular Datacited by 11
  16. 2024Overcoming LLM Challenges using RAG-Driven Precision in Coffee Leaf Disease Remediationcited by 3
  17. 2025DistRAG: Towards Distance-Based Spatial Reasoning in LLMscited by 2
  18. 2025A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesiscited by 2
  19. 2025RAST: A Retrieval Augmented Spatio-Temporal Framework for Traffic Predictioncited by 1
  20. 2025Geospatial Question Answering on Historical Maps Using Spatio-Temporal Knowledge Graphs and Large Language Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
  2. 2025PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
  3. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  4. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
  5. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval
  6. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  7. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
  8. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private