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

arXiv: https://arxiv.org/abs/2509.04716 · HTML: https://mlsanity.com/paper/2509.04716/

## Key facts

- Cited by 5 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 28 of 28)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources](https://mlsanity.com/paper/2305.13269/) (2023)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering](https://mlsanity.com/paper/2202.13296/) (2022)
- [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2210.00063/) (2022)
- [Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation](https://mlsanity.com/paper/2407.10805/) (2024)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering](https://mlsanity.com/paper/2204.08109/) (2022)
- [FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering](https://mlsanity.com/paper/2306.14722/) (2023)
- [CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting](https://mlsanity.com/paper/2409.19058/) (2024)
- [Are Large Language Models a Good Replacement of Taxonomies?](https://mlsanity.com/paper/2406.11131/) (2024)
- [Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering](https://mlsanity.com/paper/2503.18172/) (2025)
- [Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection](https://mlsanity.com/paper/2109.05808/) (2021)
- [From Data Fusion to Knowledge Fusion](https://mlsanity.com/paper/1503.00302/) (2015)
- [Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions](https://mlsanity.com/paper/2501.06699/) (2025)
- [Revisiting the Solution of Meta KDD Cup 2024: CRAG](https://mlsanity.com/paper/2409.15337/) (2024)
- [Fake News Detection with Heterogeneous Transformer](https://mlsanity.com/paper/2205.03100/) (2022)
- [Cross-domain-aware Worker Selection with Training for Crowdsourced Annotation](https://mlsanity.com/paper/2406.06977/) (2024)

## Built on by (most cited first, 5 of 5)

- [GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory](https://mlsanity.com/paper/2605.01688/) (2026)
- [When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers](https://mlsanity.com/paper/2607.00394/) (2026)
- [Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering](https://mlsanity.com/paper/2607.23278/) (2026)
- [HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering](https://mlsanity.com/paper/2608.29088/) (2026)
- [Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy](https://mlsanity.com/paper/2609.12791/) (2026)

## 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%.