Knowledge_Graph
-
Domain-constrained knowledge representation: A modal framework
2026-04-06 03:12:15Chao Li, Yuru Wang, Chunyi ZhaoAbstract
Knowledge graphs store large numbers of relations efficiently, but they remain weak at representing a quieter difficulty: the meaning of a concept often shifts with the domain in which it is used. A triple such as Apple, instance-of, Company may be acceptable in one setting while being misleading or unusable in another. In most current systems, domain information is attached as metadata, qualifiers, or graph-level organization. These mechanisms help with filtering and provenance, but they usually do not alter the formal status of the assertion itself. This paper argues that domain should be treated as part of knowledge representation rather than as supplementary annotation. It introduces the Domain-Contextualized Concept Graph (DCG), a framework in which domain is written into the relation and interpreted as a modal world constraint. In the DCG form (C, R at D, C'), the marker at D identifies the world in which the relation holds. Formally, the relation is interpreted through a domain-indexed necessity operator, so that truth, inference, and conflict checking are all scoped to the relevant world. This move has three consequences: ambiguous concepts can be disambiguated at the point of representation; invalid assertions can be challenged against their domain; cross-domain relations can be connected through explicit predicates. The paper develops this claim through a Kripke-style semantics, a compact predicate system, a Prolog implementation, and mappings to RDF, OWL, and relational databases. The contribution is a representational reinterpretation of domain itself. The central claim is that many practical failures in knowledge systems begin when domain is treated as external to the assertion. DCG addresses that by giving domain a structural and computable role inside the representation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.01770
PDF
-
Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
2026-04-06 02:43:03Songyuan Yang, Weijiang Yu, Ziyu Liu, Guijian Tang, Wenjing Yang, Huibin Tan, Nong XiaoAbstract
When video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context. Appending textual or multi-clip evidence, however, forces heterogeneous signals into a single attention space. We observe diluted attention and higher cognitive load even on non-long videos. The bottleneck is not only what to retrieve but how to represent and fuse external knowledge with the video this http URL present Graph-to-Frame RAG (G2F-RAG), a training free and auditable paradigm that delivers knowledge in the visual space. On the offline stage, an agent builds a problem-agnostic video knowledge graph that integrates entities, events, spatial relations, and linked world knowledge. On the online stage, a hierarchical multi-agent controller decides whether external knowledge is needed, retrieves a minimal sufficient subgraph, and renders it as a single reasoning frame appended to the video. LMMs then perform joint reasoning in a unified visual domain. This design reduces cognitive load and leaves an explicit, inspectable evidence trail.G2F-RAG is plug-and-play across backbones and scales. It yields consistent gains on diverse public benchmarks, with larger improvements in knowledge-intensive settings. Ablations further confirm that knowledge representation and delivery matter. G2F-RAG reframes retrieval as visual space knowledge fusion for robust and interpretable video reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2604.04372
PDF
-
GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering
2026-04-06 02:12:30Tianyi Zhang, Andreas MarfurtAbstract
Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus on RAG systems for long-document question answering. Current approaches suffer from a heavy reliance on LLM descriptions resulting in high resource consumption and latency, repetitive content across hierarchical levels, and hallucinations due to no or limited grounding in the source text. To improve both efficiency and factual accuracy through grounding, we propose GroundedKG-RAG, a RAG system in which the knowledge graph is explicitly extracted from and grounded in the source document. Specifically, we define nodes in GroundedKG as entities and actions, and edges as temporal or semantic relations, with each node and edge grounded in the original sentences. We construct GroundedKG from semantic role labeling (SRL) and abstract meaning representation (AMR) parses and then embed it for retrieval. During querying, we apply the same transformation to the query and retrieve the most relevant sentences from the grounded source text for question answering. We evaluate GroundedKG-RAG on examples from the NarrativeQA dataset and find that it performs on par with a state-of-the art proprietary long-context model at smaller cost and outperforms a competitive baseline. Additionally, our GroundedKG is interpretable and readable by humans, facilitating auditing of results and error analysis.
Abstract (translated)
检索增强生成（RAG）系统因其能在提升生成质量的同时减少所需输入上下文长度，已被广泛应用于当代大语言模型（LLMs）中。本研究聚焦于长文档问答场景下的RAG系统。当前方法存在严重依赖大语言模型自身描述导致资源消耗高、延迟大，层级间内容重复，以及因缺乏或有限依据于原文而产生的幻觉问题。为通过依据原文同时提升效率与事实准确性，我们提出GroundedKG-RAG——一种将知识图谱显式地从源文档中提取并锚定于原文的RAG系统。具体而言，我们将GroundedKG中的节点定义为实体与动作，边定义为时序或语义关系，且每个节点与边均锚定于原文句子。我们通过语义角色标注（SRL）和抽象语义表示（AMR）解析构建GroundedKG，并对其进行嵌入以用于检索。查询时，我们对问题应用相同转换，并从锚定原文中检索最相关句子以进行问答。我们在NarrativeQA数据集示例上评估GroundedKG-RAG，发现其以更小成本达到与先进专有长上下文模型相当的性能，并优于竞争性基线。此外，我们的GroundedKG具有人类可解释且可读的特性，便于结果审计与错误分析。
URL
https://arxiv.org/abs/2604.04359
PDF
-
Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification
2026-04-05 17:10:18Xinyan Ma (Harbin Institute of Technology, Harbin, China), Xianhao Ou (Harbin Institute of Technology, Harbin, China), Weihao Zhang (Harbin Institute of Technology, Harbin, China), Shixin Jiang (Harbin Institute of Technology, Harbin, China), Runxuan Liu (Harbin Institute of Technology, Harbin, China), Dandan Tu (Huawei Technologies Co., Ltd., Beijing, China), Lei Chen (Bay Area International Business School, Beijing Normal University, Beijing, China), Ming Liu (Harbin Institute of Technology, Harbin, China), Bing Qin (Harbin Institute of Technology, Harbin, China)Abstract
Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.
Abstract (translated)
知识图谱（KGs）是人工智能系统的重要基础，但其自动化构建过程不可避免地引入噪声，影响数据可信度。现有的基于图嵌入或语言模型的三元组验证方法，往往因过度依赖内部结构约束或外部语义证据而存在单源偏差，且通常遵循静态推理范式。因此，这些方法难以处理复杂或长尾事实，且可解释性有限。针对上述局限，本文提出SHARP（模式感知混合智能可靠预测系统），一种无需训练的自主智能体，将三元组验证重构为动态的战略规划、主动调查与证据推理过程。具体而言，SHARP通过记忆增强机制与模式感知战略规划提升推理稳定性，并采用增强型ReAct循环与混合知识工具集，动态整合知识图谱内部结构与外部文本证据进行交叉验证。在FB15K-237和Wikidata5M-Ind数据集上的实验表明，SHARP显著超越现有最优基线，准确率分别提升4.2%和12.9%。此外，SHARP为每个判断提供透明的、基于事实的证据链，在复杂验证任务中展现出强大的可解释性与鲁棒性。
URL
https://arxiv.org/abs/2604.04190
PDF
-
Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative Engine Optimization
2026-04-04 09:17:37XinYu Zhao, ChengYou Li, XiangBao Meng, Kai Zhang, XiaoDong LiuAbstract
Generative Engine Optimization (GEO) is rapidly reshaping digital marketing paradigms in the era of Large Language Models (LLMs). However, current GEO strategies predominantly rely on Retrieval-Augmented Generation (RAG), which inherently suffers from probabilistic hallucinations and the "zero-click" paradox, failing to establish sustainable commercial trust. In this paper, we systematically deconstruct the probabilistic flaws of existing RAG-based GEO and propose a paradigm shift towards deterministic multi-agent intent routing. First, we mathematically formulate Semantic Entropy Drift (SED) to model the dynamic decay of confidence curves in LLMs over continuous temporal and contextual perturbations. To rigorously quantify optimization value in black-box commercial engines, we introduce the Isomorphic Attribution Regression (IAR) model, leveraging a Multi-Agent System (MAS) probe with strict human-in-the-loop physical isolation to enforce hallucination penalties. Furthermore, we architect the Deterministic Agent Handoff (DAH) protocol, conceptualizing an Agentic Trust Brokerage (ATB) ecosystem where LLMs function solely as intent routers rather than final answer generators. We empirically validate this architecture using EasyNote, an industrial AI meeting minutes product by Yishu Technology. By routing the intent of "knowledge graph mapping on an infinite canvas" directly to its specialized proprietary agent via DAH, we demonstrate the reduction of vertical task hallucination rates to near zero. This work establishes a foundational theoretical framework for next-generation GEO and paves the way for a well-ordered, deterministic human-AI collaboration ecosystem.
Abstract (translated)
生成引擎优化（GEO）正在大语言模型（LLM）时代迅速重塑数字营销范式。然而，当前GEO策略主要依赖检索增强生成（RAG），其固有缺陷在于概率性幻觉与“零点击”悖论，难以建立可持续的商业信任。本文系统解构了现有基于RAG的GEO的概率性缺陷，并提出向确定性多智能体意图路由的范式转变。首先，我们通过数学公式化语义熵漂移（SED），建模LLM在连续时空扰动下置信曲线的动态衰减。为严格量化黑盒商业引擎的优化价值，我们引入同构归因回归（IAR）模型，采用具备严格人机物理隔离的多智能体系统（MAS）探针以实施幻觉惩罚机制。此外，我们构建了确定性智能体移交（DAH）协议，构想出智能体信任经纪（ATB）生态——其中LLM仅作为意图路由器而非最终答案生成器。我们通过易书科技（Yishu Technology）的工业级AI会议纪要产品EasyNote对该架构进行实证验证：通过DAH协议将“无限画布上的知识图谱映射”意图直接路由至其专有智能体，我们将垂直任务幻觉率降至近零。本研究为下一代GEO建立了基础理论框架，并为构建有序的确定性人机协作生态铺平道路。
URL
https://arxiv.org/abs/2604.03656
PDF
-
MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
2026-04-04 07:14:01Sijun Dai, Qiang Huang, Xiaoxing You, Jun YuAbstract
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while current graph-based methods rely on costly ``translation-to-text'' pipelines that discard fine-grained visual information. To address these limitations, we propose \textbf{MG$^2$-RAG}, a lightweight \textbf{M}ulti-\textbf{G}ranularity \textbf{G}raph \textbf{RAG} framework that jointly improves graph construction, modality fusion, and cross-modal retrieval. MG$^2$-RAG constructs a hierarchical multimodal knowledge graph by combining lightweight textual parsing with entity-driven visual grounding, enabling textual entities and visual regions to be fused into unified multimodal nodes that preserve atomic evidence. Building on this representation, we introduce a multi-granularity graph retrieval mechanism that aggregates dense similarities and propagates relevance across the graph to support structured multi-hop reasoning. Extensive experiments across four representative multimodal tasks (i.e., retrieval, knowledge-based VQA, reasoning, and classification) demonstrate that MG$^2$-RAG consistently achieves state-of-the-art performance while reducing graph construction overhead with an average 43.3$\times$ speedup and 23.9$\times$ cost reduction compared with advanced graph-based frameworks.
Abstract (translated)
检索增强生成（RAG）可缓解多模态大语言模型（MLLMs）中的幻觉问题，但现有系统在复杂跨模态推理方面仍存在不足。扁平向量检索常忽略结构依赖关系，而当前基于图的方法依赖成本高昂的“文本转换流水线”，会丢失细粒度的视觉信息。为应对这些局限，我们提出了\textbf{MG$^2$-RAG}，一个轻量级的\textbf{多粒度图RAG}框架，可协同优化图构建、模态融合与跨模态检索。MG$^2$-RAG通过结合轻量级文本解析与实体驱动的视觉定位，构建分层多模态知识图，使文本实体与视觉区域融合为保留原子证据的统一多模态节点。基于该表示，我们引入了多粒度图检索机制，通过聚合密集相似度并在图中传播相关性，支持结构化多跳推理。在四个代表性多模态任务（检索、基于知识视觉问答、推理与分类）上的大量实验表明，MG$^2$-RAG持续达到最先进性能，同时相较于先进基于图框架，图构建开销平均降低43.3倍，成本减少23.9倍。
URL
https://arxiv.org/abs/2604.04969
PDF
-
Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
2026-04-04 04:29:50Albert Sadowski, Jaros{\l}aw A. ChudziakAbstract
AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a ``trust-building investment'' for one strategic goal and a ``contractual liability'' for another. Current memory architectures assume a single correct encoding, or at best support multiple views over unified storage. We propose Rashomon Memory: an architecture where parallel goal-conditioned agents encode experiences according to their priorities and negotiate at query time through argumentation. Each perspective maintains its own ontology and knowledge graph. At retrieval, perspectives propose interpretations, critique each other's proposals using asymmetric domain knowledge, and Dung's argumentation semantics determines which proposals survive. The resulting attack graph is itself an explanation: it records which interpretation was selected, which alternatives were considered, and on what grounds they were rejected. We present a proof-of-concept showing that retrieval modes (selection, composition, conflict surfacing) emerge from attack graph topology, and that the conflict surfacing mode, where the system reports genuine disagreement rather than forcing resolution, lets decision-makers see the underlying interpretive conflict directly.
Abstract (translated)
在长时间运行中，AI代理会积累服务于多个并发目标的经验，且往往需要对同一事件保持相互冲突的解释。例如，在客户谈判中做出的让步，对一个战略目标而言编码为“信任建设投资”，而对另一个目标则编码为“合同责任”。现有记忆架构通常假设存在唯一正确的编码方式，或最多支持在统一存储上提供多重视角。我们提出“罗生门记忆”（Rashomon Memory）：一种并行目标条件代理根据各自优先级编码经验，并在查询时通过辩论进行协商的架构。每个视角维护各自的本体论和知识图。检索时，各视角提出解释提案，利用不对称领域知识相互批评，并通过邓格的辩论语义决定哪些提案得以保留。由此产生的攻击图本身即是一种解释：它记录了所选解释、所考虑的替代方案，以及拒绝它们的依据。我们展示的概念验证表明，检索模式（选择、组合、冲突浮现）可从攻击图拓扑中自然涌现，且冲突浮现模式——即系统报告真实分歧而非强制解决——能让决策者直接洞察底层的解释冲突。
URL
https://arxiv.org/abs/2604.03588
PDF
-
Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents
2026-04-03 22:41:35Mohammad Sadeq Abolhasani, Yang Ba, Yixuan He, Rong PanAbstract
Knowledge graph construction typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global organization, especially in long technical documents with dense, context-dependent information. We propose TRACE-KG (Text-dRiven schemA for Context-Enriched Knowledge Graphs), a multimodal framework that jointly constructs a context-enriched knowledge graph and an induced schema without assuming a predefined ontology. TRACE-KG captures conditional relations through structured qualifiers and organizes entities and relations using a data-driven schema that serves as a reusable semantic scaffold while preserving full traceability to the source evidence. Experiments show that TRACE-KG produces structurally coherent, traceable knowledge graphs and offers a practical alternative to both ontology-driven and schema-free construction pipelines.
Abstract (translated)
知识图谱构建通常依赖于预定义本体或无模式抽取。本体驱动的流程能保证类型一致性，但需要高昂的模式设计与维护成本；而无模式方法常产生碎片化图谱，全局组织性较弱，尤其在信息密集、依赖上下文的冗长技术文档中表现明显。本文提出TRACE-KG（面向上下文增强知识图谱的文本驱动模式），一种无需预定义本体的多模态框架，可联合构建上下文增强的知识图谱并自动归纳模式。该系统通过结构化限定词捕捉条件关系，并利用数据驱动模式组织实体与关系——该模式既作为可复用的语义支架，又保持对源证据的完全可追溯性。实验表明，TRACE-KG能生成结构连贯、可追溯的知识图谱，为传统本体驱动与无模式构建流程提供了实用替代方案。
URL
https://arxiv.org/abs/2604.03496
PDF
-
Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG
2026-04-03 16:23:51Jaafer Klila, Sondes Bannour Souihi, Rahma Boujelben, Nasredine Semmar, Lamia Hadrich BelguithAbstract
The injection of domain-specific knowledge is crucial for adapting language models (LMs) to specialized fields such as biomedicine. While most current approaches rely on unstructured text corpora, this study explores two complementary strategies for leveraging structured knowledge from the UMLS Metathesaurus: (i) Continual pretraining that embeds knowledge into model parameters, and (ii) Graph Retrieval-Augmented Generation (GraphRAG) that consults a knowledge graph at inference time. We first construct a large-scale biomedical knowledge graph from UMLS (3.4 million concepts and 34.2 million relations), stored in Neo4j for efficient querying. We then derive a ~100-million-token textual corpus from this graph to continually pretrain two models: BERTUMLS (from BERT) and BioBERTUMLS (from BioBERT). We evaluate these models on six BLURB (Biomedical Language Understanding and Reasoning Benchmark) datasets spanning five task types and evaluate GraphRAG on the two QA (Question Answering) datasets (PubMedQA, BioASQ). On BLURB tasks, BERTUMLS improves over BERT, with the largest gains on knowledge-intensive QA. Effects on BioBERT are more nuanced, suggesting diminishing returns when the base model already encodes substantial biomedical text knowledge. Finally, augmenting LLaMA 3-8B with our GraphRAG pipeline yields over than 3 points accuracy on PubMedQA and 5 points on BioASQ without any retraining, delivering transparent, multi-hop, and easily updated knowledge access. We release the processed UMLS Neo4j graph to support reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2604.16422
PDF
-
AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs
2026-04-03 15:26:51Zahra Makki Nayeri, Mohsen RezvaniAbstract
Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approaches lack the semantic depth required for path reasoning over attacker-victim interactions. We address this by first modelling network alerts as a knowledge graph, then formulating hyper-relational alert prediction as a hyper-relational knowledge graph completion (HR-KGC) problem, representing each network alert as a qualified statement (h, r, t, Q), where h and t are source and destination IPs, r denotes the attack type, and Q encodes flow-level metadata such as timestamps, ports, protocols, and attack intensity, going beyond standard KGC binary triples (h, r, t) that would discard this contextual richness. We introduce five models across three contributions: first, Hyper-relational Neural Bellman-Ford (HR-NBFNet) extends Neural Bellman-Ford Networks to the hyper-relational setting with qualifier-aware multi-hop path reasoning, while its multi-task variant MT-HR-NBFNet jointly predicts tail, relation, and qualifier-value within a single traversal pass; second, AlertStar fuses qualifier context and structural path information entirely in embedding space via cross-attention and learned path composition, and its multi-task extension MT-AlertStar eliminates the overhead of full knowledge graph propagation; third, HR-NBFNet-CQ extends qualifier-aware representations to answer complex first-order logic queries, including one-hop, two-hop chain, two-anchor intersection, and union, enabling multi-condition threat reasoning over the alert knowledge graph. Evaluated inductively on the Warden and UNSW-NB15 benchmarks across three qualifier-density regimes, AlertStar and MT-AlertStar achieve superior MR, MRR, and Hits@k, demonstrating that local qualifier fusion is both sufficient and more efficient than global path propagation for hyper-relational alert prediction.
Abstract (translated)
网络攻击的规模与复杂性持续增长，但现有网络入侵检测方法在攻击者-受害者交互的路径推理上缺乏所需的语义深度。本研究通过以下方式解决该问题：首先将网络告警建模为知识图谱，进而将超关系告警预测形式化为超关系知识图谱补全（HR-KGC）问题，将每个网络告警表示为限定语句（h, r, t, Q），其中h与t分别为源IP与目的IP，r表示攻击类型，Q则编码流级元数据（如时间戳、端口、协议及攻击强度），超越了会丢弃此类上下文信息的标准KGC二元三元组（h, r, t）。我们提出五个模型，涵盖三项核心贡献：第一，超关系神经贝尔曼-福特网络（HR-NBFNet）将神经贝尔曼-福特网络扩展至超关系场景，实现感知限定符的多跳路径推理，其多任务变体MT-HR-NBFNet可在单次遍历中联合预测尾实体、关系及限定符值；第二，AlertStar通过交叉注意力与学习路径组合，完全在嵌入空间内融合限定符上下文与结构路径信息，其多任务扩展MT-AlertStar消除了完整知识图谱传播的开销；第三，HR-NBFNet-CQ将感知限定符的表示扩展至复杂一阶逻辑查询应答，包括单跳、双跳链式、双锚点交集与并集查询，从而支持对告警知识图谱的多条件威胁推理。在Warden与UNSW-NB15基准的三种限定符密度情境下进行归纳评估，AlertStar与MT-AlertNet在MR、MRR及Hits@k指标上表现最优，证明局部限定符融合对于超关系告警预测既充分且比全局路径传播更高效。
URL
https://arxiv.org/abs/2604.03104
PDF
-
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
2026-04-03 10:42:07Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao HuangAbstract
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems demonstrate inherent resistance to traditional RAG attacks, such as text poisoning and prompt injection. However, in this paper, we find that the security of GraphRAG systems fundamentally relies on the topological integrity of the underlying graph, which can be undermined by implicitly corrupting the logical connections, without altering surface-level text semantics. To exploit this vulnerability, we propose \textsc{LogicPoison}, a novel attack framework that targets logical reasoning rather than injecting false contents. Specifically, \textsc{LogicPoison} employs a type-preserving entity swapping mechanism to perturb both global logic hubs for disrupting overall graph connectivity and query-specific reasoning bridges for severing essential multi-hop inference paths. This approach effectively reroutes valid reasoning into dead ends while maintaining surface-level textual plausibility. Comprehensive experiments across multiple benchmarks demonstrate that \textsc{LogicPoison} successfully bypasses GraphRAG's defenses, significantly degrading performance and outperforming state-of-the-art baselines in both effectiveness and stealth. Our code is available at \textcolor{blue}this https URL.
Abstract (translated)
基于图的检索增强生成（GraphRAG）通过将回答锚定在结构化知识图谱上，增强了大型语言模型（LLMs）的推理能力。利用社区检测和关系过滤技术，GraphRAG系统对传统的RAG攻击（如文本投毒和提示注入）表现出固有抵抗力。然而，本文发现GraphRAG系统的安全性根本上依赖于底层图的拓扑完整性，而该完整性可能在不改变表面文本语义的情况下，通过隐式破坏逻辑连接而被削弱。为利用此漏洞，我们提出了\textsc{LogicPoison}，一种针对逻辑推理而非注入虚假内容的新型攻击框架。具体而言，\textsc{LogicPoison}采用类型保持的实体交换机制，同时扰动全局逻辑枢纽以破坏整体图连通性，并切断查询特定推理桥梁以阻断关键的多跳推理路径。该方法在保持表面文本合理性的同时，有效将有效推理引入死胡同。在多个基准测试上的综合实验表明，\textsc{LogicPoison}成功绕过了GraphRAG的防御，显著降低了其性能，并在有效性和隐蔽性上均优于最先进基线方法。代码已公开于\this https URL。
URL
https://arxiv.org/abs/2604.02954
PDF
-
LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
2026-04-03 08:31:22Luc Pommeret (STL), Thomas Gerald (LISN), Patrick Paroubek (STL), Sahar Ghannay (STL), Christophe Servan (STL, AMIAD), Sophie Rosset (LISN, STL)Abstract
Knowledge Graph construction from natural language requires extracting structured triplets from complex, information-dense sentences. In this paper, we investigate if the decomposition of text into atomic propositions (minimal, semantically autonomous units of information) can improve the triplet extraction. We introduce MPropositionneur-V2, a small multilingual model covering six European languages trained by knowledge distillation from Qwen3-32B into a Qwen3-0.6B architecture, and we evaluate its integration into two extraction paradigms: entity-centric (GLiREL) and generative (Qwen3). Experiments on SMiLER, FewRel, DocRED and CaRB show that atomic propositions benefit weaker extractors (GLiREL, CoreNLP, 0.6B models), improving relation recall and, in the multilingual setting, overall accuracy. For stronger LLMs, a fallback combination strategy recovers entity recall losses while preserving the gains in relation extraction. These results show that atomic propositions are an interpretable intermediate data structure that complements extractors without replacing them.
Abstract (translated)
从自然语言构建知识图谱需要从复杂、信息密集的句子中提取结构化三元组。本文研究了将文本分解为原子命题（最小、语义自足的信息单元）是否能改进三元组抽取。我们引入了MPropositionneur-V2，一个覆盖六种欧洲语言的小型多语言模型，通过将Qwen3-32B的知识蒸馏至Qwen3-0.6B架构中进行训练，并评估了其整合到两种抽取范式中的效果：以实体为中心（GLiREL）和生成式（Qwen3）。在SMiLER、FewRel、DocRED和CaRB上的实验表明，原子命题有益于较弱的抽取器（GLiREL、CoreNLP、0.6B模型），提高了关系召回率，并在多语言设置中提升了整体准确率。对于更强大的大语言模型，一种回退组合策略在保持关系抽取增益的同时，恢复了实体召回率的损失。这些结果表明，原子命题是一种可解释的中间数据结构，能够补充而非替代抽取器。
URL
https://arxiv.org/abs/2604.02866
PDF
-
When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
2026-04-03 06:40:04Linyu Li, Zhi Jin, Yichi Zhang, Dongming Jin, Yuanpeng He, Haoran Duan, Gadeng Luosang, Nyima TashiAbstract
Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge graph reasoning (CKGR) methods focus on structural triples and cannot fully exploit multimodal signals from new entities. Existing multimodal knowledge graph reasoning (MMKGR) methods, however, usually assume static graphs and suffer catastrophic forgetting as graphs evolve. To address this gap, we present a systematic study of continual multimodal knowledge graph reasoning (CMMKGR). We construct several continual multimodal knowledge graph benchmarks from existing MMKG datasets and propose MRCKG, a new CMMKGR model. Specifically, MRCKG employs a multimodal-structural collaborative curriculum to schedule progressive learning based on the structural connectivity of new triples to the historical graph and their multimodal compatibility. It also introduces a cross-modal knowledge preservation mechanism to mitigate forgetting through entity representation stability, relational semantic consistency, and modality anchoring. In addition, a multimodal contrastive replay scheme with a two-stage optimization strategy reinforces learned knowledge via multimodal importance sampling and representation alignment. Experiments on multiple datasets show that MRCKG preserves previously learned multimodal knowledge while substantially improving the learning of new knowledge.
Abstract (translated)
现实世界中的多模态知识图谱（MMKGs）具有动态性，新实体、关系及多模态知识会随时间不断涌现。现有持续知识图谱推理（CKGR）方法仅关注结构三元组，无法充分利用新实体的多模态信号；而现有多模态知识图谱推理（MMKGR）方法通常假设图谱静态，在动态演化中易出现灾难性遗忘。为填补这一空白，我们对持续多模态知识图谱推理（CMMKGR）进行了系统性研究：基于现有MMKG数据集构建了多个持续多模态知识图谱基准，并提出了新型CMMKGR模型MRCKG。具体而言，MRCKG采用多模态-结构协同课程机制，依据新三元组与历史图谱的结构关联性及其多模态兼容性规划渐进式学习；引入跨模态知识保持机制，通过实体表征稳定性、关系语义一致性与模态锚定缓解遗忘问题；此外，设计多模态对比回放方案与两阶段优化策略，借助多模态重要性采样与表征对齐强化已学知识。多数据集实验表明，MRCKG在高效学习新知识的同时，能有效保持已掌握的多模态知识。
URL
https://arxiv.org/abs/2604.02778
PDF
-
OntoKG: Ontology-Oriented Knowledge Graph Construction with Intrinsic-Relational Routing
2026-04-03 01:17:51Yitao Li, Zhanlin Liu, Anuranjan Pandey, Muni SrikanthAbstract
Organizing a large-scale knowledge graph into a typed property graph requires structural decisions -- which entities become nodes, which properties become edges, and what schema governs these choices. Existing approaches embed these decisions in pipeline code or extract relations ad hoc, producing schemas that are tightly coupled to their construction process and difficult to reuse for downstream ontology-level tasks. We present an ontology-oriented approach in which the schema is designed from the outset for ontology analysis, entity disambiguation, domain customization, and LLM-guided extraction -- not merely as a byproduct of graph building. The core mechanism is intrinsic-relational routing, which classifies every property as either intrinsic or relational and routes it to the corresponding schema module. This routing produces a declarative schema that is portable across storage backends and independently reusable. We instantiate the approach on the January 2026 Wikidata dump. A rule-based cleaning stage identifies a 34.6M-entity core set from the full dump, followed by iterative intrinsic-relational routing that assigns each property to one of 94 modules organized into 8 categories. With tool-augmented LLM support and human review, the schema reaches 93.3% category coverage and 98.0% module assignment among classified entities. Exporting this schema yields a property graph with 34.0M nodes and 61.2M edges across 38 relationship types. We validate the ontology-oriented claim through five applications that consume the schema independently of the construction pipeline: ontology structure analysis, benchmark annotation auditing, entity disambiguation, domain customization, and LLM-guided extraction.
Abstract (translated)
将大规模知识图谱组织为类型化属性图需要做出结构性决策——哪些实体成为节点，哪些属性成为边，以及由何种模式来规范这些选择。现有方法将这些决策嵌入流水线代码或临时提取关系，产生的模式与其构建过程紧密耦合，难以在后续本体级任务中复用。我们提出一种面向本体的方法，其模式从一开始就为本体分析、实体消歧、领域定制和LLM引导的提取而设计——而不仅仅是图构建的副产品。核心机制是内嵌-关系路由，它将每个属性分类为内嵌属性或关系属性，并将其路由到相应的模式模块。这种路由产生了一种声明式模式，可跨存储后端移植，并能独立复用。我们在2026年1月的Wikidata数据转储上实现了该方法。基于规则的清洗阶段从完整转储中识别出3460万实体的核心集合，随后进行迭代内嵌-关系路由，将每个属性分配到按8个类别组织的94个模块中。在工具增强的LLM支持和人工审核下，该模式在已分类实体中达到93.3%的类别覆盖率和98.0%的模块分配率。导出此模式可生成一个包含3400万个节点和6120万条边、涵盖38种关系类型的属性图。我们通过五种独立于构建流水线消费该模式的应用来验证面向本体的主张：本体结构分析、基准标注审计、实体消歧、领域定制和LLM引导的提取。
URL
https://arxiv.org/abs/2604.02618
PDF
-
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
2026-04-03 01:11:43Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui LiAbstract
Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an LLM-based agentic framework that automates end-to-end verification of technical claims without requiring domain expertise. AutoVerifier decomposes every technical assertion into structured claim triples of the form (Subject, Predicate, Object), constructing knowledge graphs that enable structured reasoning across six progressively enriching layers: corpus construction and ingestion, entity and claim extraction, intra-document verification, cross-source verification, external signal corroboration, and final hypothesis matrix generation. We demonstrate AutoVerifier on a contested quantum computing claim, where the framework, operated by analysts with no quantum expertise, automatically identified overclaims and metric inconsistencies within the target paper, traced cross-source contradictions, uncovered undisclosed commercial conflicts of interest, and produced a final assessment. These results show that structured LLM verification can reliably evaluate the validity and maturity of emerging technologies, turning raw technical documents into traceable, evidence-backed intelligence assessments.
Abstract (translated)
科技与工程情报（S&TI）分析需要验证快速增长的文献中复杂的技术声明，而现有方法无法弥合表面准确性与深层方法学有效性之间的验证差距。我们提出了AutoVerifier——一个基于大语言模型的智能体框架，可在无需领域专家的情况下实现技术声明端到端的自动化验证。AutoVerifier将每项技术断言分解为（主体、谓语、客体）结构的声明三元组，构建支持六层递进式结构化推理的知识图谱：语料库构建与输入、实体与声明提取、文档内验证、跨源验证、外部信号佐证以及最终假设矩阵生成。我们在一个有争议的量子计算声明案例中验证了AutoVerifier：由无量子专业背景的分析师操作，该框架自动识别出目标论文中的过度宣称与指标不一致问题，追溯了跨源矛盾，发现了未披露的商业利益冲突，并生成了最终评估报告。这些结果表明，结构化大语言模型验证能够可靠评估新兴技术的有效性与成熟度，将原始技术文档转化为可追溯、有证据支撑的情报评估。
URL
https://arxiv.org/abs/2604.02617
PDF
-
Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
2026-04-02 21:54:33Naga Sowjanya Barla, Jacopo de BerardinisAbstract
The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or "hallucinations" makes them unreliable for heritage applications where veracity is a central requirement. To address this, we propose a novel neuro-symbolic architecture grounded in Knowledge Graphs (KGs) that establishes a transparent "plan-retrieve-generate" workflow for story generation. A key novelty of our approach is the repurposing of competency questions (CQs) - traditionally design-time validation artifacts - into run-time executable narrative plans. This approach bridges the gap between high-level user personas and atomic knowledge retrieval, ensuring that generation is evidence-closed and fully auditable. We validate this architecture using a new resource: the Live Aid KG, a multimodal dataset aligning 1985 concert data with the Music Meta Ontology and linking to external multimedia assets. We present a systematic comparative evaluation of three distinct Retrieval-Augmented Generation (RAG) strategies over this graph: a purely symbolic KG-RAG, a text-enriched Hybrid-RAG, and a structure-aware Graph-RAG. Our experiments reveal a quantifiable trade-off between the factual precision of symbolic retrieval, the contextual richness of hybrid methods, and the narrative coherence of graph-based traversal. Our findings offer actionable insights for designing personalised and controllable storytelling systems.
Abstract (translated)
非物质文化遗产的保护是一项关键挑战，因为集体记忆会随时间逐渐消逝。尽管大语言模型（LLMs）为生成引人入胜的叙事提供了前景可期的途径，但其产生事实错误或“幻觉”的倾向使其在真实性为核心要求的遗产应用中并不可靠。为应对这一问题，我们提出了一种基于知识图谱（KGs）的新型神经符号架构，该架构建立了透明的“规划-检索-生成”叙事生成工作流。本方法的关键创新在于将能力问题（CQs）——传统上作为设计阶段验证工件——重新利用为运行时可执行的叙事规划。该方法弥合了高层用户画像与原子级知识检索之间的鸿沟，确保生成过程具备证据封闭性且完全可审计。 我们利用一项新资源——Live Aid知识图谱对该架构进行验证：这是一个多模态数据集，将1985年演唱会数据与音乐元本体对齐，并链接至外部多媒体资源。我们在此图谱上系统比较了三种不同的检索增强生成（RAG）策略：纯符号化的知识图谱检索增强生成、文本增强的混合检索增强生成，以及结构感知的图检索增强生成。实验揭示了符号检索的事实精确性、混合方法的语境丰富性与基于图谱遍历的叙事连贯性之间存在可量化的权衡。我们的研究结果为设计个性化且可控的叙事系统提供了可操作的见解。
URL
https://arxiv.org/abs/2604.02545
PDF
-
Opal: Private Memory for Personal AI
2026-04-02 21:23:00Darya Kaviani, Alp Eren Ozdarendeli, Jinhao Zhu, Yu Ding, Raluca Ada PopaAbstract
Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trusted hardware can keep this data private, but struggles to scale with a growing datastore. This pushes the data to external storage, which exposes retrieval access patterns that leak private information to the application provider. Oblivious RAM (ORAM) is a cryptographic primitive that can hide these patterns, but it requires a fixed access budget, precluding the query-dependent traversals that agentic memory systems rely on for accuracy. We present Opal, a private memory system for personal AI. Our key insight is to decouple all data-dependent reasoning from the bulk of personal data, confining it to the trusted enclave. Untrusted disk then sees only fixed, oblivious memory accesses. This enclave-resident component uses a lightweight knowledge graph to capture personal context that semantic search alone misses and handles continuous ingestion by piggybacking reindexing and capacity management on every ORAM access. Evaluated on a comprehensive synthetic personal-data pipeline driven by stochastic communication models, Opal improves retrieval accuracy by 13 percentage points over semantic search and achieves 29x higher throughput with 15x lower infrastructure cost than a secure baseline. Opal is under consideration for deployment to millions of users at a major AI provider.
Abstract (translated)
个人AI系统日益长期保留用户活动记忆，包括文档、邮件、消息、会议及环境录音。可信硬件虽能保障此类数据隐私，却难以随数据存储规模增长而扩展。这迫使数据转移至外部存储，导致检索访问模式暴露，向应用提供商泄露隐私信息。不经意随机存储器（ORAM）是一种可隐藏访问模式的密码学原语，但其要求固定访问预算，无法支持智能体记忆系统依赖的动态查询遍历以保障准确性。本文介绍Opal——一款面向个人AI的隐私记忆系统。核心洞见在于：将所有数据依赖推理与海量个人数据解耦，将其限制在可信执行环境中。此时非可信磁盘仅能观察到固定且不经意的内存访问。该驻留可信区的组件采用轻量级知识图谱，捕获语义搜索单独遗漏的个人上下文，并通过在每次ORAM访问中“搭车”执行重索引与容量管理，实现持续数据摄入。基于随机通信模型驱动的综合合成个人数据管道评估显示，Opal相比语义搜索将检索准确率提升13个百分点，相较于安全基线实现29倍吞吐量提升与15倍基础设施成本降低。Opal正被某大型AI提供商考虑部署至数百万用户。
URL
https://arxiv.org/abs/2604.02522
PDF
-
SAFE: Stepwise Atomic Feedback for Error correction in Multi-hop Reasoning
2026-04-02 12:59:30Daeyong Kwon, Soyoung Yoon, Seung-won HwangAbstract
Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that replaces the ungrounded Chain-of-Thought (CoT) with a strictly verifiable sequence of grounded entities. Our framework operates across two phases: (1) train-time verification, where we establish an atomic error taxonomy and a Knowledge Graph (KG)-grounded verification pipeline to eliminate noisy supervision in standard benchmarks, identifying up to 14% of instances as unanswerable, and (2) inference-time verification, where a feedback model trained on this verified dataset dynamically detects ungrounded steps in real-time. Experimental results demonstrate that SAFE not only exposes the critical flaws of existing benchmarks at train-time, but also significantly outperforms standard baselines, achieving an average accuracy gain of 8.4 pp while guaranteeing verifiable trajectories at inference-time.
Abstract (translated)
多跳问答基准测试经常奖励大语言模型（LLMs）的虚假正确性，掩盖了其缺乏依据或存在缺陷的推理步骤。为转向严谨推理，我们提出了SAFE——一个动态基准测试框架，该框架用严格可验证的可验证实体序列取代了无依据的思维链（CoT）。我们的框架包含两个阶段：（1）训练时验证，在此阶段我们建立了原子级错误分类体系和一个基于知识图谱（KG）的验证流程，以消除标准基准中的噪声监督，识别出高达14%的不可回答实例；（2）推理时验证，在此阶段一个在此已验证数据集上训练的反馈模型能实时动态检测无依据的步骤。实验结果表明，SAFE不仅在训练时暴露了现有基准的关键缺陷，而且在推理时显著超越标准基线，实现了平均8.4个百分点的准确率提升，同时保证了可验证的推理轨迹。
URL
https://arxiv.org/abs/2604.01993
PDF
-
KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answering
2026-04-01 08:06:37Xianyao Zheng, Hong Yu, Hui Cui, Changming Sun, Xiangyu Li, Ran Su, Leyi Wei, Jia Zhou, Junbo Wang, Qiangguo JinAbstract
Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent methods fail to fully leverage domain-specific medical knowledge, making it difficult to accurately associate lesion features in medical images with key diagnostic criteria. Additionally, classification-based approaches typically rely on predefined answer sets. Treating Med-VQA as a simple classification problem limits its ability to adapt to the diversity of free-form answers and may overlook detailed semantic information in those answers. To address these challenges, we propose a knowledge graph enhanced cross-Mamba interaction (KG-CMI) framework, which consists of a fine-grained cross-modal feature alignment (FCFA) module, a knowledge graph embedding (KGE) module, a cross-modal interaction representation (CMIR) module, and a free-form answer enhanced multi-task learning (FAMT) module. The KG-CMI learns cross-modal feature representations for images and texts by effectively integrating professional medical knowledge through a graph, establishing associations between lesion features and disease knowledge. Moreover, FAMT leverages auxiliary knowledge from open-ended questions, improving the model's capability for open-ended Med-VQA. Experimental results demonstrate that KG-CMI outperforms existing state-of-the-art methods on three Med-VQA datasets, i.e., VQA-RAD, SLAKE, and OVQA. Additionally, we conduct interpretability experiments to further validate the framework's effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2604.00601
PDF
-
Ontology-based knowledge graph infrastructure for interoperable atomistic simulation data
2026-03-31 20:01:20Abril Azocar Guzman, Sarath Menon, Tilmann Hickel, Stefan SandfeldAbstract
The reuse of atomistic simulation data is often limited by heterogeneous formats, incomplete metadata, and a lack of standardized representations of workflows and provenance. Here we present an ontology-based infrastructure for representing and integrating atomistic simulation data as a knowledge graph. The approach combines domain ontologies with a software framework that enables data capture both from existing datasets and directly from simulation workflows at the point of generation. Heterogeneous data from multiple sources are normalized into a common, ontology-aligned representation, enabling consistent querying and analysis across datasets. We demonstrate these capabilities through the integration of grain boundary data, cross-dataset analysis of material properties, and extraction of derived thermodynamic quantities from existing simulations. In addition, workflows are represented in a machine-readable form, enabling both forward provenance tracking and partial reconstruction of computational procedures. The resulting knowledge graph contains over 750,000 triples describing nearly 8,000 computational samples. This work provides a practical framework for improving the findability, interoperability, and reuse of atomistic simulation data.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06230
PDF
