Research map / Large language models / Retrieval and knowledge
Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question Answering
Yunfeng Ning, Mayi Xu, Jintao Wen, Qiankun Pi, Yuanyuan Zhu, Ming Zhong, Jiawei Jiang, Tieyun Qian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Relation-centric Abstraction (entity abstraction from adjacent relations) (ablation) | ARoG · CWQ (#Filtered) | Hits@1: 30.1 -> 36.3 | Improved |
| add Structure-oriented Abstraction (abstract concept paths) (ablation) | ARoG · CWQ (#Total) | Hits@1: 50.3 -> 60.0 | Improved |
| add Structure-oriented Abstraction (ablation) | ARoG · WebQSP (#Total) | Hits@1: 68.1 -> 74.7 | Improved |
| add relation filtering (Step 2) on top of entity abstraction (ablation) | ARoG · CWQ (#Total) | Hits@1: 59.5 -> 60.0 | Improved |
| add relation filtering (Step 2) on top of entity abstraction (ablation) | ARoG · WebQSP (#Filtered) | Hits@1: 58.9 -> 58.9 | No clear effect |
| replace abstract concept path with CoT rationales (ablation) | ARoG · WebQSP, CWQ, GrailQA | Hits@1 | Hurt |
| replace abstract concept path with question decomposition (ablation) | ARoG · WebQSP, CWQ, GrailQA | Hits@1 | Hurt |
| anonymize entities in the generation phase for ToG (ablation) | ToG · WebQSP, CWQ, GrailQA | Hits@1 | Hurt |
| replace Abstraction-driven Retrieval with LLM-based entity retrieval (ARoG-R) when entities anonymous in retrieval (ablation) | ARoG · WebQSP, CWQ, GrailQA | Hits@1 | Hurt |
| increase retrieval depth (ablation) | ARoG · WebQSP | Hits@1 | No clear effect |
| increase retrieval width (ablation) | ARoG · WebQSP | Hits@1 | Improved |
| increase retrieval depth beyond 2 (ablation) | ARoG · CWQ, GrailQA | Hits@1 | No clear effect |
Closest papers by meaning
- SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG (NeurIPS 2025 · similarity 0.88)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.87)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.87)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.86)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.86)
- Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
