Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs
By: Mauro Dalle Lucca Tosi, Jordi Cabot
Potential Business Impact:
Keeps private data safe when asking computers questions.
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.
Similar Papers
LLM-empowered knowledge graph construction: A survey
Artificial Intelligence
Helps computers understand and organize information better.
Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph
Computation and Language
Helps chatbots give better answers using your personal info.
Are Large Language Models Effective Knowledge Graph Constructors?
Computation and Language
Helps computers build better knowledge maps.