Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation

• URL: http://arxiv.org/abs/2508.09460v1
• Date: Wed, 13 Aug 2025 03:35:32 GMT
• Title: Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation
• Authors: Xujie Yuan, Shimin Di, Jielong Tang, Libin Zheng, Jian Yin,
• Abstract summary: Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models.<n>Existing KG-RAG frameworks operate as open-loop systems, suffering from cognitive blindness.<n>We propose Metacognitive Knowledge Graph Retrieval Augmented Generation (MetaKGRAG) to enable path-aware, closed-loop refinement.
• Score: 11.752268960775075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) significantly enhances the reasoning capabilities of LargeLanguage Models by leveraging structured knowledge. However, existing KG-RAG frameworks typically operate as open-loop systems, suffering from cognitive blindness, an inability to recognize their exploration deficiencies. This leads to relevance drift and incomplete evidence, which existing self-refinement methods, designed for unstructured text-based RAG, cannot effectively resolve due to the path-dependent nature of graph exploration. To address this challenge, we propose Metacognitive Knowledge Graph Retrieval Augmented Generation (MetaKGRAG), a novel framework inspired by the human metacognition process, which introduces a Perceive-Evaluate-Adjust cycle to enable path-aware, closed-loop refinement. This cycle empowers the system to self-assess exploration quality, identify deficiencies in coverage or relevance, and perform trajectory-connected corrections from precise pivot points. Extensive experiments across five datasets in the medical, legal, and commonsense reasoning domains demonstrate that MetaKGRAG consistently outperforms strong KG-RAG and self-refinement baselines. Our results validate the superiority of our approach and highlight the critical need for path-aware refinement in structured knowledge retrieval.

Related papers

• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs [10.861331756147477]
  We propose TruthfulRAG to resolve factual-level knowledge conflicts in RAG systems.<n>TruthfulRAG constructs Knowledge Graphs (KGs) by systematically extracting triples from retrieved content.<n>Extensive experiments reveal that TruthfulRAG outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-13T14:49:44Z)
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [88.82814893945077]
  Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge.<n>Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them.<n>G-reasoner is a unified framework that integrates graph and language foundation models for reasoning over diverse graph-structured knowledge.
  arXiv  Detail & Related papers  (2025-09-29T04:38:12Z)
• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases [0.0]
  This paper introduces OntoRAG, an automated pipeline designed to derive from unstructured knowledge bases.<n>OntoRAG integrates advanced techniques, including web scraping, PDF parsing, hybrid chunking, information extraction, knowledge graph construction, and ontology creation.
  arXiv  Detail & Related papers  (2025-05-31T18:33:39Z)
• RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration [4.604003661048267]
  RAG-KG-IL is a novel multi-agent hybrid framework designed to enhance the reasoning capabilities of Large Language Models.<n>It integrates Retrieval-Augmented Generation (RAG) and Knowledge Graphs (KGs) with an Incremental Learning (IL) approach.<n>We evaluate the framework using real-world case studies involving health-related queries.
  arXiv  Detail & Related papers  (2025-03-14T11:50:16Z)
• G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition [54.45837774534411]
  We introduce textbfG-OSR, a benchmark for evaluating Graph Open-Set Recognition (GOSR) methods at both the node and graph levels.<n>Results offer critical insights into the generalizability and limitations of current GOSR methods.
  arXiv  Detail & Related papers  (2025-03-01T13:02:47Z)
• StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization [94.31508613367296]
  Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) We propose StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Experiments show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios.
  arXiv  Detail & Related papers  (2024-10-11T13:52:44Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation [11.471919529192048]
  Large Language Models (LLMs) are proficient at generating coherent and contextually relevant text. Retrieval-augmented generation (RAG) systems mitigate this by incorporating external knowledge sources, such as structured knowledge graphs (KGs) Our study investigates this dilemma by analyzing error patterns in existing KG-based RAG methods and identifying eight critical failure points.
  arXiv  Detail & Related papers  (2024-07-16T23:50:07Z)
• KG-RAG: Bridging the Gap Between Knowledge and Creativity [0.0]
  Large Language Model Agents (LMAs) face issues such as information hallucinations, catastrophic forgetting, and limitations in processing long contexts. This paper introduces a KG-RAG (Knowledge Graph-Retrieval Augmented Generation) pipeline to enhance the knowledge capabilities of LMAs. Preliminary experiments on the ComplexWebQuestions dataset demonstrate notable improvements in the reduction of hallucinated content.
  arXiv  Detail & Related papers  (2024-05-20T14:03:05Z)
• Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques [5.561202401558972]
  This research elucidates the employment of reinforcement learning strategies, notably the REINFORCE algorithm, to navigate the intricacies inherent in multi-hop Knowledge Graphs (KG-R) By partitioning the Unified Medical Language System (UMLS) benchmark dataset into rich and sparse subsets, we investigate the efficacy of pre-trained BERT embeddings and Prompt Learning methodologies to refine the reward shaping process.
  arXiv  Detail & Related papers  (2024-03-09T05:34:07Z)
• Graph-level Protein Representation Learning by Structure Knowledge Refinement [50.775264276189695]
  This paper focuses on learning representation on the whole graph level in an unsupervised manner. We propose a novel framework called Structure Knowledge Refinement (SKR) which uses data structure to determine the probability of whether a pair is positive or negative.
  arXiv  Detail & Related papers  (2024-01-05T09:05:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.