EMNLP Findings2025
SKRAG: A Retrieval-Augmented Generation Framework Guided by Reasoning Skeletons over Knowledge Graphs
Abstract
In specialized domains such as space science and utilization, question answering (QA) systems are required to perform complex multifact reasoning over sparse knowledge graphs (KGs). Existing KG-based retrieval-augmented generation (RAG) frameworks often face challenges such as inefficient subgraph retrieval, limited reasoning capabilities, and high computational costs. These issues limit their effectiveness in specialized domains. In this paper, we propose SKRAG, a novel Skeleton-guided RAG framework for knowledge graph question answering (KGQA). SKRAG leverages a lightweight language model enhanced with the Finite State Machine (FSM) constraint to produce structurally grounded reasoning skeletons, which guide accurate subgraph retrieval. The retrieved subgraph is then used to prompt a general large language model (LLM) for answer generation. We also introduce SSUQA, a KGQA dataset in the space science and utilization domain. Experiments show that SKRAG outperforms strong baselines on SSUQA and two general-domain benchmarks, demonstrating its adaptability and practical effectiveness.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Large Language Models are Zero-Shot Reasoners cites Language Models are Few-Shot Learners
- Retrieval Augmentation Reduces Hallucination in Conversation cites Language Models are Few-Shot Learners
- Finetuned Language Models are Zero-Shot Learners cites Language Models are Few-Shot Learners
- On the Planning Abilities of Large Language Models - A Critical Investigation cites Large Language Models are Zero-Shot Reasoners
- On the Planning Abilities of Large Language Models - A Critical Investigation cites Language Models are Few-Shot Learners
Builds on19
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- Retrieval Augmentation Reduces Hallucination in ConversationKurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela et al.EMNLP Findings 2021 · 579 citations
- On the Planning Abilities of Large Language Models - A Critical InvestigationKarthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao KambhampatiNeurIPS 2023 · 509 citations
Related papers
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented GenerationMufei Li, Siqi Miao, Pan LiICLR 2025
- mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQAXu Yuan, Liangbo Ning, Qingqing Ye, Wenqi Fan et al.SIGIR 2026 · 2 citations
- FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge GraphsZengyi Gao, Yukun Cao, Hairu Wang, Ao Ke et al.ACL Findings 2025 · 14 citations
- KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question AnsweringYushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang et al.EMNLP Findings 2025 · 7 citations
- Iterative Knowledge Graph Refinement and Integration for Medical Question AnsweringHaochen Zou, Yongli WangACL Findings 2026
