paper
Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation
paperactiveprovisional
achieving-precise-text-to-cypher-via-grounded-knowledge-graph-data-generation-454579ca·1 events·first seen 2d agoAliases: Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation
Co-occurring entities
More like this (12)
counterfactual text generationDetecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphsknowledge graphText Generation InferenceGraph Transformerknowledge graph promptingKnowledge Graph Random Walkchain-of-thought training data generationgenerative language modelingA Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge GraphsProvenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data CurationSpeaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
Recent events (1)
Synthetic data generation method enables small LLMs to match large models on Text-To-Cypher tasks
A new arXiv paper presents an automatic synthetic data generation method for fine-tuning small LLMs on Text-To-Cypher (Text2Cypher) parsing, enabling natural language interfaces to property graph databases. Experiments across major Text-To-Cypher benchmarks show that small fine-tuned models can compete with much larger proprietary models. The approach is positioned as a solution for local deployment scenarios requiring data sovereignty without expensive annotation.