Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs

• URL: http://arxiv.org/abs/2512.04852v1
• Date: Thu, 04 Dec 2025 14:37:00 GMT
• Title: Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs
• Abstract summary: We propose a privacy-aware query generation approach for knowledge graphs (KGs)<n>Our method identifies sensitive information in the graph based on its structure and omits such values before requesting the LLM to translate natural language questions into Cypher queries.<n> Experimental results show that our approach preserves the quality of the generated queries while preventing sensitive data from being transmitted to third-party services.
• Score: 2.338361654308822
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used to query knowledge graphs (KGs) due to their strong semantic understanding and extrapolation capabilities compared to traditional approaches. However, these methods cannot be applied when the KG contains sensitive data and the user lacks the resources to deploy a local generative LLM. To address this issue, we propose a privacy-aware query generation approach for KGs. Our method identifies sensitive information in the graph based on its structure and omits such values before requesting the LLM to translate natural language questions into Cypher queries. Experimental results show that our approach preserves the quality of the generated queries while preventing sensitive data from being transmitted to third-party services.

Related papers

• A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering [41.99844472131922]
  Large Language Models excel at language understanding but are limited in knowledge-intensive domains.<n>This work introduces an interactive framework in which LLMs generate and explain Cypher graph queries.
  arXiv  Detail & Related papers  (2026-02-05T10:10:19Z)
• KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering [23.818060996900837]
  Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge.<n>We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR)<n>KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs.
  arXiv  Detail & Related papers  (2025-11-06T06:06:54Z)
• Enhancing Manufacturing Knowledge Access with LLMs and Context-aware Prompting [9.520082987178851]
  Large Language Models (LLMs) can automatically translate natural language queries into the SPARQL format.<n>We evaluate strategies that use LLMs as mediators to facilitate information retrieval from Knowledge graphs (KGs)<n>Our findings show that LLMs can significantly improve their performance on generating correct and complete queries when provided only the adequate context of the KG schema.
  arXiv  Detail & Related papers  (2025-07-30T12:39:01Z)
• SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection [81.78173888579941]
  Large Language Models (LLMs) are considered a well-suited method to increase the quality of the question-answering functionality.<n>LLMs are trained on web data, where researchers have no control over whether the benchmark or the knowledge graph was already included in the training data.<n>This paper introduces a novel method that evaluates the quality of LLMs by generating a SPARQL query from a natural-language question.
  arXiv  Detail & Related papers  (2025-07-18T12:28:08Z)
• Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation [89.65955788873532]
  Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP)<n>We propose a novel framework named GenKI, which aims to improve the OpenQA performance by exploring Knowledge Integration and controllable Generation.
  arXiv  Detail & Related papers  (2025-05-26T08:18:33Z)
• Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models [51.47994645529258]
  We propose Question-Aware Knowledge Graph Prompting (QAP), which incorporates question embeddings into GNN aggregation to dynamically assess KG relevance.<n> Experimental results demonstrate that QAP outperforms state-of-the-art methods across multiple datasets, highlighting its effectiveness.
  arXiv  Detail & Related papers  (2025-03-30T17:09:11Z)
• Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference [82.557441484339]
  We propose a method to detect the knowledge boundary of Vision Large Language Models (VLLMs)<n> Experimental results on various types of Visual Question Answering datasets show that our method successfully depicts a VLLM's knowledge boundary.
  arXiv  Detail & Related papers  (2025-02-25T09:32:08Z)
• Knowledge Graph-Enhanced Large Language Models via Path Selection [58.228392005755026]
  Large Language Models (LLMs) have shown unprecedented performance in various real-world applications. LLMs are known to generate factually inaccurate outputs, a.k.a. the hallucination problem. We propose a principled framework KELP with three stages to handle the above problems.
  arXiv  Detail & Related papers  (2024-06-19T21:45:20Z)
• Redefining Information Retrieval of Structured Database via Large Language Models [10.117751707641416]
  This paper introduces a novel retrieval augmentation framework called ChatLR. It primarily employs the powerful semantic understanding ability of Large Language Models (LLMs) as retrievers to achieve precise and concise information retrieval. Experimental results demonstrate the effectiveness of ChatLR in addressing user queries, achieving an overall information retrieval accuracy exceeding 98.8%.
  arXiv  Detail & Related papers  (2024-05-09T02:37:53Z)
• Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context [4.1229332722825]
  This paper introduces a novel framework that combines graph-driven context retrieval in conjunction to knowledge graphs based enhancement. We conduct experiments on various Large Language Models (LLMs) with different parameter sizes to evaluate their ability to ground knowledge and determine factual accuracy in answers to open-ended questions. Our methodology GraphContextGen consistently outperforms dominant text-based retrieval systems, demonstrating its robustness and adaptability to a larger number of use cases.
  arXiv  Detail & Related papers  (2024-01-23T11:25:34Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.