https://ym-xu.github.io/living-survey/fields/rag/#tag=graphKnowledge graphs, GraphRAG and structured stores as the retrieval layer.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.11010https://arxiv.org/abs/2611.11010Sat, 07 Nov 2026 00:00:00 +0000Uday Allu Graph-based retrieval-augmented generation (GraphRAG) improves multi-hop question answering, but deployed systems face two costs that research comparisons rarely measure: building the graph, and removing documents from it. We present Lightfoot, a GraphRAG system in which every entity, link, fact and synonym edge is a d…https://arxiv.org/abs/2611.09866https://arxiv.org/abs/2611.09866Fri, 06 Nov 2026 00:00:00 +0000Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, et al. Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burden by leveraging rec…https://arxiv.org/abs/2611.09658https://arxiv.org/abs/2611.09658Fri, 06 Nov 2026 00:00:00 +0000Jie Fu, Yuan Hong, Yue Ning, Wendy Hui Wang Graph Retrieval-Augmented Generation (GraphRAG) connects information across documents through entity relationships to support relational reasoning. However, black-box access to GraphRAG systems can enable adversaries to reconstruct knowledge graphs and recover both structural connectivity between entities and the seman…https://arxiv.org/abs/2611.09414https://arxiv.org/abs/2611.09414Fri, 06 Nov 2026 00:00:00 +0000Rosario Napoli, Antonio Celesti, Massimo Villari, Maria Fazio Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. Howeve…https://arxiv.org/abs/2611.06481https://arxiv.org/abs/2611.06481Wed, 04 Nov 2026 00:00:00 +0000Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, et al. Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-c…https://arxiv.org/abs/2610.40971https://arxiv.org/abs/2610.40971Thu, 29 Oct 2026 00:00:00 +0000Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of a knowledge graph. Multimodal GraphRAG systems describe each entity in text, and text conveys little of the visual detai…https://arxiv.org/abs/2610.38366https://arxiv.org/abs/2610.38366Wed, 28 Oct 2026 00:00:00 +0000Xinxun Zhang, Yuxiang Wang, Shanshan Feng, Jun Zhang, et al. Recent advances in large language models (LLMs) have spurred growing interest in temporal knowledge graph question answering (TKGQA). Most existing methods rely on semantic retrieval augmented generation (RAG), which suffers from fundamental limitations in complex temporal reasoning. On the one hand, semantic-based RAG…https://arxiv.org/abs/2610.37728https://arxiv.org/abs/2610.37728Tue, 27 Oct 2026 00:00:00 +0000Fakabbir Amin A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information using the latest information and metadata available outside the scope of organizational documentation responsibility. We investigated whether using a…https://arxiv.org/abs/2610.37237https://arxiv.org/abs/2610.37237Tue, 27 Oct 2026 00:00:00 +0000Wadie El Amrani, Luis Galárraga GraphRAG systems often use knowledge graphs to retrieve relevant context for an LLM that produces the final answer. That makes answers more inscrutable and therefore less appealing for domains where transparency is paramount. We present GraphRAGProv, an architecture that executes SPARQL queries over source-grounded RDF…https://arxiv.org/abs/2610.36650https://arxiv.org/abs/2610.36650Tue, 27 Oct 2026 00:00:00 +0000Amiri Hayes, Kristina Wicke Graph-structured representations of text data have become foundational across machine learning, yet it remains unclear how to systematically construct a graph from a given dataset for a target task. Choices about which entities become nodes, which relationships become edges, and what text each node contains can substan…https://arxiv.org/abs/2610.35412https://arxiv.org/abs/2610.35412Mon, 26 Oct 2026 00:00:00 +0000Jiate Liu, Liuyi Chen, Xiaofei Yuan, Yifu Tang, et al. Graph-based retrieval-augmented generation (GraphRAG) answers multi-hop questions by organizing a corpus into a graph and retrieving along its structure. Existing retrieval methods face two limitations. Diffusion- and similarity-based methods expand retrieval along fixed edge weights or by similarity to the question, w…https://arxiv.org/abs/2610.34866https://arxiv.org/abs/2610.34866Mon, 26 Oct 2026 00:00:00 +0000Zicheng Zhao, Linhao Luo, Zongji Yu, Junnan Dong, et al. Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge. Graph Retrieval-Augmented Generation (GraphRAG) addresses this challenge by organizing fragment knowledge as graphs, while recent Graph Foundation M…https://arxiv.org/abs/2610.33511https://arxiv.org/abs/2610.33511Sat, 24 Oct 2026 00:00:00 +0000Kaifeng Jin, Yuchen Yan, Zhichen Zeng, Xiao Lin, et al. Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured knowledge. Despite extensive efforts, existing methods still face two key gaps. The first is an architectural gap: existing …https://arxiv.org/abs/2610.30728https://arxiv.org/abs/2610.30728Thu, 22 Oct 2026 00:00:00 +0000Xiaobao Wang, Renda Han, Zhiliang Xia, Meng Liu, et al. Graph Retrieval-Augmented Generation (GraphRAG) leverages centralized knowledge graphs to enhance large language models with structured knowledge retrieval. However, real-world knowledge is inherently distributed across multiple organizations rather than being centrally accessible. Privacy constraints further prohibit …https://arxiv.org/abs/2610.30710https://arxiv.org/abs/2610.30710Thu, 22 Oct 2026 00:00:00 +0000Guangcan Li, Shuyuan Zheng, Jiayao Liu, Shigeto Seno, et al. Over-representation analysis (ORA) is widely used to interpret gene-expression studies, but its outputs are often fragmented across gene-set databases and presented as flat term lists that obscure gene-level links among related enrichment signals. We propose Graph-Based Over-Representation Retrieval-Augmented Generatio…https://arxiv.org/abs/2610.19549https://arxiv.org/abs/2610.19549Wed, 14 Oct 2026 00:00:00 +0000Yining Tang, Junyu Zhang, Haomiao Qiu, Yongchao Liu, et al. Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its security depends on both the seed chunks retrieved for a query and the graph evidence assembled from them, yet attacks on this evidence path remain underexplored. We in…https://arxiv.org/abs/2610.13695https://arxiv.org/abs/2610.13695Fri, 09 Oct 2026 00:00:00 +0000Ibrahim Siddig, Sviatoslav Tugeev, Munir Georges Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augmented Generation (RAG) attempts to ground the generative process in t…https://arxiv.org/abs/2610.13296https://arxiv.org/abs/2610.13296Fri, 09 Oct 2026 00:00:00 +0000Cheuk Hei Chung, Li Liu High-precision retrieval over external knowledge bases is essential for LLM agents to operate effectively. However, existing Information Retrieval (IR) research primarily optimizes query-side retrievers (e.g., ColBERT, BGE) and generators (e.g., Self-RAG, GraphRAG), while reducing corpus-side representation to chunking…https://arxiv.org/abs/2610.13128https://arxiv.org/abs/2610.13128Fri, 09 Oct 2026 00:00:00 +0000Wenlin Lin, Fanzhe Wei Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-retrieval knowledge-point in…https://arxiv.org/abs/2610.09360https://arxiv.org/abs/2610.09360Wed, 07 Oct 2026 00:00:00 +0000Ruochi Li, Jianzhe Lin, Haoxuan Zhang, Haihua Chen, et al. · NeurIPS 2026 Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such documents therefore requires more than retrieving relevant passages: systems must recover the evidence topology that connects heterogeneous evidence units. Existing Grap…https://arxiv.org/abs/2610.09026https://arxiv.org/abs/2610.09026Tue, 06 Oct 2026 00:00:00 +0000Kemal Davaslioglu, Nathan Conger, Sastry Kompella, Yalin E. Sagduyu, et al. We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings such as suicide prevention, where effective assessment requires integrating heterogeneous clinical, behavioral, social, and temporal evidence. BEACON-S…https://arxiv.org/abs/2610.08205https://arxiv.org/abs/2610.08205Tue, 06 Oct 2026 00:00:00 +0000Nikolaos D. Tantaroudas, Ilias Karachalios, Andrew J. McCracken Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-augmented generation (RAG). We compare the two on KyGround, a benchmark of 198 questions drawn from the published records of a Greek--English agricultural platform on Kyt…https://arxiv.org/abs/2610.02373https://arxiv.org/abs/2610.02373Thu, 01 Oct 2026 00:00:00 +0000Jisung Park, John Le, Heath Cooper GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioritised at query time. Prior attacks target only instance-level components (nodes, edges, triples), overlooking these schema-level structures. W…https://arxiv.org/abs/2609.37661https://arxiv.org/abs/2609.37661Tue, 29 Sep 2026 00:00:00 +0000Baoxian Liu, Tong Wei Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activa…https://arxiv.org/abs/2609.35304https://arxiv.org/abs/2609.35304Mon, 28 Sep 2026 00:00:00 +0000Antonios Georgakopoulos, Paul Groth, Lise Stork Multimodal knowledge graphs (KGs) integrate information from text, figures, tables, and other modalities into a unified structured representation, with the promise that richer evidence enables better inference. In GraphRAG systems built over such graphs, it is commonly assumed that retrieving evidence from more modalit…https://arxiv.org/abs/2609.29282https://arxiv.org/abs/2609.29282Thu, 24 Sep 2026 00:00:00 +0000Qi Sun, Yijia Zhang, Caibo Li, Qiang Li, et al. While graph-based and hypergraph-based Retrieval-Augmented Generation (RAG) significantly mitigate hallucinations in Large Language Models (LLMs), existing structure-based RAG systems typically adopt static traversal strategies regardless of the query complexity. We identify this ``static retrieval fallacy'' as a prima…https://arxiv.org/abs/2609.27009https://arxiv.org/abs/2609.27009Tue, 22 Sep 2026 00:00:00 +0000Qingjing Chen, Junkai Zhang, Shaochun Wang, Jiahao Ding, et al. · EMNLP 2026 Findings Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenges. First, existing RAG and GraphRAG methods emphasize lexical or semantic similarity while overlooking normative relations among legal provisions. Second, vanilla Chain…https://arxiv.org/abs/2609.25991https://arxiv.org/abs/2609.25991Tue, 22 Sep 2026 00:00:00 +0000Jiangxu Wu Retrieval-augmented generation (RAG) gives large language models (LLMs) access to external knowledge, but its conventional retrieve-concatenate-generate pipeline makes retrieval decisions on behalf of the model. As tool use and agent loops become more reliable, an agent can decide whether to retrieve, what to inspect, …https://arxiv.org/abs/2609.24346https://arxiv.org/abs/2609.24346Mon, 21 Sep 2026 00:00:00 +0000Senlei Zhang, Linhao Luo, Qian-Wen Zhang, Siyu An, et al. Graph Retrieval-Augmented Generation (GraphRAG) has remarkably enhanced large language models on complex reasoning by leveraging structured entity topologies. However, existing frameworks heavily rely on standard autoregressive language models where the nature of inherent sequential generation severely hinders overall …https://arxiv.org/abs/2609.19622https://arxiv.org/abs/2609.19622Thu, 17 Sep 2026 00:00:00 +0000Zeliang Li, Xiaofen Xing, Kailing Guo, Wenyu Tao, et al. Existing Retrieval-Augmented Generation (RAG) systems struggle with multi-hop reasoning due to a fundamental inability to balance relevance and novelty. Traditional dense retrievers are constrained by surface-level matching, falling into a homogenized "Similarity Trap". Conversely, emerging Graph RAGs attempt to explor…https://arxiv.org/abs/2609.14572https://arxiv.org/abs/2609.14572Sun, 13 Sep 2026 00:00:00 +0000Sushan Adhikari Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must handle formal proofs and asymptotic reasoning that conventional resources rarely explain in an adaptive, on-demand way. We present AlgoRAG, a specialized Retrieval-Augmente…https://arxiv.org/abs/2609.12791https://arxiv.org/abs/2609.12791Fri, 11 Sep 2026 00:00:00 +0000Gengxian Zhou, Jian Xu, Zichen Tang, Shiming Xiang, et al. · EMNLP 2026 Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge bases (large-scale knowledge graphs and text corpora) for complex reasoning remains a challenge. Existing methods typically employ reactive, graph-driv…https://arxiv.org/abs/2609.12464https://arxiv.org/abs/2609.12464Fri, 11 Sep 2026 00:00:00 +0000Nilesh Jaiswal, Aniket Agrawal, Arjit Shukla, Divya Malhotra, et al. As enterprises modernize legacy monolithic systems to microservices, Large Language Models (LLMs) are heavily utilized for automated code translation. However, traditional vector-based Retrieval-Augmented Generation (Standard RAG) struggles to capture topological relationships. It fetches isolated chunks that sever inh…https://arxiv.org/abs/2609.11569https://arxiv.org/abs/2609.11569Thu, 10 Sep 2026 00:00:00 +0000Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small gr…https://arxiv.org/abs/2609.11493https://arxiv.org/abs/2609.11493Thu, 10 Sep 2026 00:00:00 +0000Reza Amirmoshiri, Faryad Sahneh, Yasser Jangjou Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-intensive continuum from drug discovery to commercial manufacturing. This knowledge is traditionally fragmented across functions and heterogeneous formats, causing traceabi…https://arxiv.org/abs/2609.11065https://arxiv.org/abs/2609.11065Thu, 10 Sep 2026 00:00:00 +0000EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, et al. Graph Retrieval-Augmented Generation (GraphRAG) can connect evidence distributed across a corpus graph, but most systems use largely shared exploration procedures across queries. This creates a structural mismatch: direct facts may need compact local neighborhoods, comparisons need balanced coverage of multiple targets…https://arxiv.org/abs/2609.10239https://arxiv.org/abs/2609.10239Wed, 09 Sep 2026 00:00:00 +0000Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditione…https://arxiv.org/abs/2609.05139https://arxiv.org/abs/2609.05139Fri, 04 Sep 2026 00:00:00 +0000Zheng Kui Lin Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed across chapters, relations evolve over narrative time, and correct answers may depend jointly on temporal, spatial, and relational constraints. We propose NS-ST-GraphRAG…https://arxiv.org/abs/2609.04442https://arxiv.org/abs/2609.04442Thu, 03 Sep 2026 00:00:00 +0000John Seon Keun Yi, Joshua R. Minot, Dokyun Lee · EMNLP 2026 Workshop Large language models deployed in high-stakes settings frequently generate plausible but ungrounded claims. Standard retrieval-augmented generation (RAG) pipelines offer limited remedy, since they retrieve isolated passages without tracking cross-document evidence relationships or quantifying uncertainty. We introduce …https://arxiv.org/abs/2609.02954https://arxiv.org/abs/2609.02954Wed, 02 Sep 2026 00:00:00 +0000Huiyuan Xie, Yuqin Huang, Zhicheng Hao, Yida Cai, et al. Identifying the issues disputed between litigating parties is a crucial component of real-world litigation. However, legal issues remain comparatively underexplored in legal AI research. In this work, we study the computational modelling of legal issue identification in litigation. We introduce a legally grounded hiera…