AI Paper Atlas

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

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Relation-centric Abstraction (entity abstraction from adjacent relations) (ablation)ARoG · CWQ (#Filtered)Hits@1: 30.1 -> 36.3Improved
add Structure-oriented Abstraction (abstract concept paths) (ablation)ARoG · CWQ (#Total)Hits@1: 50.3 -> 60.0Improved
add Structure-oriented Abstraction (ablation)ARoG · WebQSP (#Total)Hits@1: 68.1 -> 74.7Improved
add relation filtering (Step 2) on top of entity abstraction (ablation)ARoG · CWQ (#Total)Hits@1: 59.5 -> 60.0Improved
add relation filtering (Step 2) on top of entity abstraction (ablation)ARoG · WebQSP (#Filtered)Hits@1: 58.9 -> 58.9No clear effect
replace abstract concept path with CoT rationales (ablation)ARoG · WebQSP, CWQ, GrailQAHits@1Hurt
replace abstract concept path with question decomposition (ablation)ARoG · WebQSP, CWQ, GrailQAHits@1Hurt
anonymize entities in the generation phase for ToG (ablation)ToG · WebQSP, CWQ, GrailQAHits@1Hurt
replace Abstraction-driven Retrieval with LLM-based entity retrieval (ARoG-R) when entities anonymous in retrieval (ablation)ARoG · WebQSP, CWQ, GrailQAHits@1Hurt
increase retrieval depth (ablation)ARoG · WebQSPHits@1No clear effect
increase retrieval width (ablation)ARoG · WebQSPHits@1Improved
increase retrieval depth beyond 2 (ablation)ARoG · CWQ, GrailQAHits@1No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy