mlsanityData to 7 Oct 2026

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

arXiv 2509.04716 ↗First posted 5 Sep 2025cs.CL cs.AI cs.IRcited by 5

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based RAG pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. Our retrieval-filtering-summarization approach, combined with fine-tuned LLMs for Chain-of-Thought reasoning on knowledge sub-graphs, reduces noises and improves QA for both simple and complex questions. Experiments demonstrate that KERAG surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 59 references that are in the map. First posted on arXiv 5 Sep 2025.

Builds on

28 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul

Other references · 27

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 641
  4. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  6. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
  7. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  8. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  9. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 167
  10. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  11. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  12. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
15 more
  1. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  2. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  3. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  4. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  5. 2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
  6. 2023FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answeringcited by 21
  7. 2024Are Large Language Models a Good Replacement of Taxonomies?cited by 19
  8. 2024CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecastingcited by 19
  9. 2025Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answeringcited by 14
  10. 2021Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersectioncited by 12
  11. 2015From Data Fusion to Knowledge Fusioncited by 10
  12. 2025Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questionscited by 8
  13. 2024Revisiting the Solution of Meta KDD Cup 2024: CRAGcited by 5
  14. 2022Fake News Detection with Heterogeneous Transformercited by 4
  15. 2024Cross-domain-aware Worker Selection with Training for Crowdsourced Annotationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memorycited by 2
  2. 2026When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Bufferscited by 1
  3. 2026Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answeringcited by 0
  4. 2026HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answeringcited by 0
  5. 2026Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
  2. 2025Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
  3. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
  4. 2024Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation
  5. 2026RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
  6. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  7. 2025MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
  8. 2025What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge