Ontology
-
A Benchmark for Gap and Overlap Analysis as a Test of KG Task Readiness
2026-04-12 23:18:47Maruf Ahmed Mridul, Rohit Kapa, Oshani SeneviratneAbstract
Task-oriented evaluation of knowledge graph (KG) quality increasingly asks whether an ontology-based representation can answer the competency questions that users actually care about, in a manner that is reproducible, explainable, and traceable to evidence. This paper adopts that perspective and focuses on gap and overlap analysis for policy-like documents (e.g., insurance contracts), where given a scenario, which documents support it (overlap) and which do not (gap), with defensible justifications. The resulting gap/overlap determinations are typically driven by genuine differences in coverage and restrictions rather than missing data, making the task a direct test of KG task readiness rather than a test of missing facts or query expressiveness. We present an executable and auditable benchmark that aligns natural-language contract text with a formal ontology and evidence-linked ground truth, enabling systematic comparison of methods. The benchmark includes: (i) ten simplified yet diverse life-insurance contracts reviewed by a domain expert, (ii) a domain ontology (TBox) with an instantiated knowledge base (ABox) populated from contract facts, and (iii) 58 structured scenarios paired with SPARQL queries with contract-level outcomes and clause-level excerpts that justify each label. Using this resource, we compare a text-only LLM baseline that infers outcomes directly from contract text against an ontology-driven pipeline that answers the same scenarios over the instantiated KG, demonstrating that explicit modeling improves consistency and diagnosis for gap/overlap analyses. Although demonstrated for gap and overlap analysis, the benchmark is intended as a reusable template for evaluating KG quality and supporting downstream work such as ontology learning, KG population, and evidence-grounded question answering.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10853
PDF
-
MMRareBench: A Rare-Disease Multimodal and Multi-Image Medical Benchmark
2026-04-12 17:53:02Junzhi Ning, Jiashi Lin, Yingying Fang, Wei Li, Jiyao Liu, Cheng Tang, Chenglong Ma, Wenhao Tang, Tianbin Li, Ziyan Huang, Guang Yang, Junjun HeAbstract
Multimodal large language models (MLLMs) have advanced clinical tasks for common conditions, but their performance on rare diseases remains largely untested. In rare-disease scenarios, clinicians often lack prior clinical knowledge, forcing them to rely strictly on case-level evidence for clinical judgments. Existing benchmarks predominantly evaluate common-condition, single-image settings, leaving multimodal and multi-image evidence integration under rare-disease data scarcity systematically unevaluated. We introduce MMRareBench, to our knowledge the first rare-disease benchmark jointly evaluating multimodal and multi-image clinical capability across four workflow-aligned tracks: diagnosis, treatment planning, cross-image evidence alignment, and examination suggestion. The benchmark comprises 1,756 question-answer pairs with 7,958 associated medical images curated from PMC case reports, with Orphanet-anchored ontology alignment, track-specific leakage control, evidence-grounded annotations, and a two-level evaluation protocol. A systematic evaluation of 23 MLLMs reveals fragmented capability profiles and universally low treatment-planning performance, with medical-domain models trailing general-purpose MLLMs substantially on multi-image tracks despite competitive diagnostic scores. These patterns are consistent with a capacity dilution effect: medical fine-tuning can narrow the diagnostic gap but may erode the compositional multi-image capability that rare-disease evidence integration demands.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10755
PDF
-
Failure Ontology: A Lifelong Learning Framework for Blind Spot Detection and Resilience Design
Abstract
Personalized learning systems are almost universally designed around a single objective: help people acquire knowledge and skills more efficiently. We argue this framing misses the more consequential problem. The most damaging failures in human life-financial ruin, health collapse, professional obsolescence-are rarely caused by insufficient knowledge acquisition. They arise from the systematic absence of entire conceptual territories from a person's cognitive map: domains they never thought to explore because, from within their existing worldview, those domains did not appear to exist or to matter. We call such absences Ontological Blind Spots and introduce Failure Ontology (F), a formal framework for detecting, classifying, and remediating them across a human lifetime. The framework introduces three original contributions: (1) a four-type taxonomy of blind spots distinguishing domain blindness, structural blindness, weight blindness, and temporal blindness; (2) five convergent failure patterns characterizing how blind spots interact with external disruption to produce catastrophic outcomes; and (3) the Failure Learning Efficiency Theorem, proving that failure-based learning achieves higher sample efficiency than success-based learning under bounded historical data. We illustrate the framework through historical case analysis of the 1997 Asian Financial Crisis and the 2008 subprime mortgage crisis, and through alongitudinal individual case study spanning five life stages.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10549
PDF
-
Ontological Trajectory Forecasting via Finite Semigroup Iteration and Lie Algebra Approximation in Geopolitical Knowledge Graphs
2026-04-11 08:12:16Qihang WuAbstract
We present EL-DRUIN, an ontological reasoning system for geopolitical intelligence analysis that combines formal ontology, finite semigroup algebra, and Lie algebra approximation to forecast long-run relationship trajectories. Current LLM-based political analysis systems operate as summarisation engines, producing outputs bounded by textual pattern matching. EL-DRUIN departs from this paradigm by modelling geopolitical relationships as states in a finite set of named Dynamic Patterns, composing patterns via a semigroup operation whose structure constants are defined by an explicit composition table, and embedding each pattern as a vector in an 8-dimensional semantic Lie algebra space. Forward simulation iterates this semigroup operation, yielding reachable pattern sets at each discrete timestep; convergence to idempotent absorbing states (fixed points of the composition) constitutes the predicted long-run attractor. Bayesian posterior weights combine ontology-derived confidence priors with a Lie similarity term measuring the cosine similarity between the vector sum of composing patterns and the target pattern vector, providing interpretable, calibrated probabilities that are not self-reported by a language model. Bifurcation points -- steps at which two candidate attractors have near-equal posterior mass -- are detected and exposed to downstream analysis. We demonstrate the framework on six geopolitical scenarios including US-China technology decoupling and the Taiwan Strait military coercion trajectory. The architecture is publicly available as an open-source system with a Streamlit frontend exposing full computation traces, Bayesian posterior breakdowns, and 8D ontological state vectors.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10087
PDF
-
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
2026-04-09 21:58:42Samah Fodeh, Ganesh Puthiaraju, Elyas Irankhah, Linhai Ma, Srivani Talakokkul, Afshan Khan, Sreeraj Ramachandran, Jordan Alpert, Sarah SchellhornAbstract
Structured prediction requires models to generate ontology-constrained labels, grounded evidence, and valid structure under ambiguity, label skew, and heterogeneous group difficulty. We present a two-part framework for controllable inference and robust fine-tuning. First, we introduce a task-agnostic prompting strategy that combines XML-based instruction structure, disambiguation rules, verification-style reasoning, schema constraints, and self-validation to address format drift, label ambiguity, evidence hallucination, and metadata-conditioned confusion in in-context structured generation. Second, we introduce STaR-DRO, a stateful robust optimization method for group heterogeneity. It combines Tsallis mirror descent with momentum-smoothed, centered group-loss signals and bounded excess-only multipliers so that only persistently hard groups above a neutral baseline are upweighted, concentrating learning where it is most needed while avoiding volatile, dense exponentiated-gradient reweighting and unnecessary loss from downweighting easier groups. We evaluate the combined framework on EPPC Miner, a benchmark for extracting hierarchical labels and evidence spans from patient-provider secure messages. Prompt engineering improves zero-shot by +15.44 average F1 across Code, Sub-code, and Span over four Llama models. Building on supervised fine-tuning, STaR-DRO further improves the hardest semantic decisions: on Llama-3.3-70B-Instruct, Code F1 rises from 79.24 to 81.47 and Sub-code F1 from 67.78 to 69.30, while preserving Span performance and reducing group-wise validation cross-entropy by up to 29.6% on the most difficult clinical categories. Because these rare and difficult groups correspond to clinically consequential communication behaviors, these gains are not merely statistical improvements: they directly strengthen communication mining reliability for patient-centered care analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09737
PDF
-
From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI
2026-04-08 06:07:48Hongyin Zhu, Jinming Liang, Mengjun Hou, Ruifan Tang, Xianbin Zhu, Jingyuan Yang, Yuanman Mao, Feng WuAbstract
Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions that are fluent but ungrounded and carrying no audit trail. We present LOM-action, which equips enterprise AI with \emph{event-driven ontology simulation}: business events trigger scenario conditions encoded in the enterprise ontology~(EO), which drive deterministic graph mutations in an isolated sandbox, evolving a working copy of the subgraph into the scenario-valid simulation graph $G_{\text{sim}}$; all decisions are derived exclusively from this evolved graph. The core pipeline is \emph{event $\to$ simulation $\to$ decision}, realized through a dual-mode architecture -- \emph{skill mode} and \emph{reasoning mode}. Every decision produces a fully traceable audit log. LOM-action achieves 93.82% accuracy and 98.74% tool-chain F1 against frontier baselines Doubao-1.8 and DeepSeek-V3.2, which reach only 24--36% F1 despite 80% accuracy -- exposing the \emph{illusive accuracy} phenomenon. The four-fold F1 advantage confirms that ontology-governed, event-driven simulation, not model scale, is the architectural prerequisite for trustworthy enterprise decision intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2604.08603
PDF
-
Compiling OpenSCENARIO 2.1 for Scenario-Based Testing in CARLA
2026-04-07 20:30:06Thoshitha Gamage, Lasanthi GamageAbstract
While the ASAM OpenSCENARIO 2.1 Domain-Specific Language (DSL) enables declarative, intent-driven authoring for Scenario-Based Testing (SBT), its integration into open-source simulators like CARLA remains limited by legacy parsers. We propose a multi-pass modern compiler architecture that translates the OpenSCENARIO 2.1 DSL directly into executable CARLA behaviors. The pipeline features an ANTLR4 frontend for Abstract Syntax Tree (AST) generation, a semantic middle-end, and a runtime backend that synthesizes deterministic py_trees behavior trees. Mapping the standardized domain ontology directly to CARLA's procedural API via a custom method registry eliminates the need for external logic solvers. A demonstrative multi-actor cut-in and evasive maneuver, selected from a wider suite of validated scenarios, confirms the compiler's ability to process concurrent actions, dynamic mathematical expressions, and asynchronous signaling. This framework establishes a functional baseline for reproducible, large-scale SBT, paving the way for future C++ optimizations to mitigate current Python-based computational overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2604.16452
PDF
-
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures
2026-04-07 15:00:01Fan Zhang (Steve), Mingzi Song (Steve), Rania Elbadry (Steve), Yankai Chen (Steve), Shaobo Wang (Steve), Yixi Zhou (Steve), Xunwen Zheng (Steve), Yueru He (Steve), Yuyang Dai (Steve), Georgi Georgiev (Steve), Ayesha Gull (Steve), Muhammad Usman Safder (Steve), Fan Wu (Steve), Liyuan Meng (Steve), Fengxian Ji (Steve), Junning Zhao (Steve), Xueqing Peng (Steve), Jimin Huang (Steve), Yu Chen (Steve), Xue (Steve), Liu, Preslav Nakov, Zhuohan XieAbstract
Financial reporting systems increasingly use large language models (LLMs) to extract and summarize corporate disclosures. However, most assume a single-market setting and do not address structural differences across jurisdictions. Variations in accounting taxonomies, tagging infrastructures (e.g., XBRL vs. PDF), and aggregation conventions make cross-jurisdiction reporting a semantic alignment and verification challenge. We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting. The system builds a unified canonical ontology over Income Statement, Balance Sheet, and Cash Flow, and decomposes reporting into auditable stages including filing acquisition, extraction, canonical mapping, and anomaly logging. Rather than using LLMs as free-form generators, FinReporting deploys them as constrained verifiers under explicit decision rules and evidence grounding. Evaluated on annual filings from the US, Japan, and China, the system improves consistency and reliability under heterogeneous reporting regimes. We release an interactive demo supporting cross-market inspection and structured export of localized financial statements. Our demo is available at this https URL . The video describing our system is available at this https URL
Abstract (translated)
财务报告系统日益采用大语言模型（LLMs）来提取和汇总企业披露信息。然而，大多数系统假设单一市场环境，未解决跨司法管辖区的结构性差异。会计准则、标签基础设施（如XBRL与PDF）及汇总惯例的差异，使跨管辖区报告成为语义对齐与验证的挑战。本文提出FinReporting，一个面向本地化跨管辖区财务报告的智能体工作流。该系统针对利润表、资产负债表和现金流量表构建统一规范本体，并将报告分解为可审计阶段，包括文件获取、提取、规范映射与异常记录。FinReporting并非将LLMs用作自由生成器，而是将其作为受明确决策规则与证据约束的验证器。通过对美国、日本和中国的年度申报文件进行评估，该系统在异构报告体系下提升了 consistency 与可靠性。我们发布了支持跨市场审查与本地化财务报表结构化导出的交互式演示，演示地址见此链接。介绍本系统的视频见此链接。
URL
https://arxiv.org/abs/2604.05966
PDF
-
OntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation
2026-04-07 06:06:45Dongying Lin, Yinan Liu, Shengwei tang, Bin Wang, Xiaochun YangAbstract
Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information within KG snapshots. A key challenge for most existing TKG extrapolation models is handling entities with sparse historical interaction. The ontological knowledge is beneficial for alleviating this sparsity issue by enabling these entities to inherit behavioral patterns from other entities with the same concept, which is ignored by previous studies. In this paper, we propose a novel encoder-decoder framework OntoTKGE that leverages the ontological knowledge from the ontology-view KG (i.e., a KG modeling hierarchical relations among abstract concepts as well as the connections between concepts and entities) to guide the TKG extrapolation model's learning process through the effective integration of the ontological and temporal knowledge, thereby enhancing entity embeddings. OntoTKGE is flexible enough to adapt to many TKG extrapolation models. Extensive experiments on four data sets demonstrate that OntoTKGE not only significantly improves the performance of many TKG extrapolation models but also surpasses many SOTA baseline methods.
Abstract (translated)
URL
https://arxiv.org/abs/2604.05468
PDF
-
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
2026-04-07 04:42:44Wenxiao Zhang, Yu Liu, Qiang sun, Yihao Ding, Sirui Li, Yanbing Liu, Jin B. Hong, Wei LiuAbstract
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce \textbf{STIndex}, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. \textbf{STIndex} integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, \textbf{STIndex} improves spatiotemporal entity extraction F1 by 4.37\% (GPT-4o-mini) and 3.60\% (Qwen3-8B). A live demonstration and open-source code are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.08597
PDF
-
A Modular Architecture for Typologically Controlled Lexicon Generation
Abstract
Constructing artificial lexicons that are pronounceable, typologically plausible, and semantically structured remains an open challenge in computational linguistics. Existing conlang generators either lack formal phonotactic guarantees or delegate generation to opaque, non-reproducible LLM-based pipelines. We propose a modular framework that samples phoneme inventories from PHOIBLE, generates word forms under interchangeable phonological grammars (deterministic, OT, and MaxEnt), and assigns meanings via a Swadesh--Leipzig--Jakarta ontology with explicit form--meaning alignment. Evaluation on character $n$-gram perplexity, log-likelihood, and KL divergence against PHOIBLE across lexicon sizes of 100-5,000 forms shows that probabilistic grammars consistently outperform deterministic and random baselines on both phonotactic coherence and typological realism.
Abstract (translated)
URL
https://arxiv.org/abs/2605.28824
PDF
-
The Indra Representation Hypothesis for Multimodal Alignment
2026-04-06 07:46:04Jianglin Lu, Hailing Wang, Kuo Yang, Yitian Zhang, Simon Jenni, Yun FuAbstract
Recent studies have uncovered an interesting phenomenon: unimodal foundation models tend to learn convergent representations, regardless of differences in architecture, training objectives, or data modalities. However, these representations are essentially internal abstractions of samples that characterize samples independently, leading to limited expressiveness. In this paper, we propose The Indra Representation Hypothesis, inspired by the philosophical metaphor of Indra's Net. We argue that representations from unimodal foundation models are converging to implicitly reflect a shared relational structure underlying reality, akin to the relational ontology of Indra's Net. We formalize this hypothesis using the V-enriched Yoneda embedding from category theory, defining the Indra representation as a relational profile of each sample with respect to others. This formulation is shown to be unique, complete, and structure-preserving under a given cost function. We instantiate the Indra representation using angular distance and evaluate it in cross-model and cross-modal scenarios involving vision, language, and audio. Extensive experiments demonstrate that Indra representations consistently enhance robustness and alignment across architectures and modalities, providing a theoretically grounded and practical framework for training-free alignment of unimodal foundation models. Our code is available at this https URL.
Abstract (translated)
近期研究揭示了一个有趣现象：无论架构、训练目标或数据模态有何差异，单模态基础模型倾向于学习收敛表示。然而这些表示本质上是独立刻画样本的内部抽象，导致表达能力受限。本文受因陀罗网哲学隐喻启发，提出因陀罗表示假说。我们认为单模态基础模型的表示正在收敛以隐式反映现实背后的共享关系结构，类似于因陀罗网的关系本体论。我们运用范畴论中的V-丰富化永田嵌入对该假说进行形式化，将因陀罗表示定义为每个样本相对于其他样本的关系轮廓。在给定代价函数下，该形式化被证明具有唯一性、完备性和结构保持性。我们通过角距离实例化因陀罗表示，并在涉及视觉、语言和音频的跨模型与跨模态场景中进行评估。大量实验表明，因陀罗表示能持续增强跨架构与跨模态的鲁棒性与对齐性，为单模态基础模型的免训练对齐提供了理论严谨且实用的框架。代码已公开于此https链接。
URL
https://arxiv.org/abs/2604.04496
PDF
-
Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation
2026-04-06 05:54:21Barbara Gendron, Ga\"el Guibon, Mathieu d'AquinAbstract
Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight, and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.
Abstract (translated)
基于大语言模型（LLMs）的对话代理近期已成为人机交互的强大工具。然而，其黑盒特性导致可预测性不足且缺乏个性化，而可控生成可解决这些问题。本研究提出一种端到端方法，通过对话相关方面的本体定义，实现对LLM输出的模块化与可解释控制。关键方面被建模为约束条件，并进一步对LLM进行微调以生成相应内容。为验证方法有效性，我们探索了两个针对核心对话方面的任务：英语 proficiency 等级与内容极性特征。通过对七个最先进的开源对话LLM采用混合微调流程，结果表明该方法持续优于预训练基线模型，甚至在较小模型上同样有效。除定量提升外，该框架保持模型无关性、轻量级与可解释性，支持可复用的控制策略并扩展至新领域与交互目标。此方法增强了与策略指令的对齐性，并证明了本体驱动控制在对话系统中的有效性。
URL
https://arxiv.org/abs/2604.04450
PDF
-
Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework
2026-04-05 00:41:09Dalal Alharthi, Ivan Roberto Kawaminami GarciaAbstract
As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models (LLMs) have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic rigor. To address these dual challenges, we propose a unified, secure-by-design GenAI framework that integrates PromptShield and the Cloud Investigation Automation Framework (CIAF). PromptShield proactively defends LLMs against adversarial prompts using ontology-driven validation that standardizes user inputs and mitigates manipulation. CIAF streamlines cloud forensic investigations through structured, ontology-based reasoning across all six phases of the forensic process. We evaluate our system on real-world datasets from AWS and Microsoft Azure, demonstrating substantial improvements in both LLM security and forensic accuracy. Experimental results show PromptShield boosts classification performance under attack conditions, achieving precision, recall, and F1 scores above 93%, while CIAF enhances ransomware detection accuracy in cloud logs using Likert-transformed performance features. Our integrated framework advances the automation, interpretability, and trustworthiness of cloud forensics and LLM-based systems, offering a scalable foundation for real-time, AI-driven incident response across diverse cloud infrastructures.
Abstract (translated)
随着云环境日益复杂，网络安全与取证调查必须不断发展以应对新兴威胁。大语言模型（LLMs）在自动化日志分析与推理任务中展现出潜力，但仍易受提示注入攻击，且缺乏取证严谨性。为应对这两大挑战，我们提出了一个统一、设计安全的生成式AI框架，整合了PromptShield与云取证自动化框架（CIAF）。PromptShield通过本体驱动验证主动防御LLMs对抗性提示，该验证标准化用户输入并缓解操纵风险。CIAF则通过基于本体的结构化推理，简化了取证全过程六个阶段的云取证调查。我们在AWS与微软Azure的真实数据集上评估了该系统，证明其在LLM安全性与取证准确性方面均有显著提升。实验结果表明，PromptShield在攻击条件下提升了分类性能，精确率、召回率与F1分数均超过93%；而CIAF通过利克特变换的性能特征，增强了云日志中的勒索软件检测准确率。我们的集成框架推动了云取证与基于LLM系统的自动化、可解释性与可信度，为跨多样云基础设施的实时AI驱动事件响应提供了可扩展基础。
URL
https://arxiv.org/abs/2604.03912
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
-
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
-
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
-
Detecting Toxic Language: Ontology and BERT-based Approaches for Bulgarian Text
2026-04-02 08:06:26Melania Berbatova, Tsvetoslav VasevAbstract
Toxic content detection in online communication remains a significant challenge, with current solutions often inadvertently blocking valuable information, including medical terms and text related to minority groups. This paper presents a more nu-anced approach to identifying toxicity in Bulgarian text while preserving access to essential information. The research explores two distinct methodologies for detecting toxic content. The developed methodologies have po-tential applications across diverse online platforms and content moderation systems. First, we propose an ontology that models the potentially toxic words in Bulgarian language. Then, we compose a dataset that comprises 4,384 manually anno-tated sentences from Bulgarian online forums across four categories: toxic language, medical terminology, non-toxic lan-guage, and terms related to minority communities. We then train a BERT-based model for toxic language classification, which reaches a 0.89 F1 macro score. The trained model is directly applicable in a real environment and can be integrated as a com-ponent of toxic content detection systems.
Abstract (translated)
在线交流中的毒性内容检测仍是一项重大挑战，现有方案常会误拦包括医学术语和少数群体相关文本在内的有价值信息。本文提出了一种更精细的保加利亚语毒性识别方法，在检测毒性的同时保留关键信息的可访问性。本研究探索了两种截然不同的毒性内容检测方法，所开发的方法论可应用于各类在线平台和内容审核系统。首先，我们构建了一个对保加利亚语潜在毒性词汇进行建模的本体。随后，我们创建了一个包含4,384条人工标注语句的数据集，这些语句来自保加利亚在线论坛，涵盖四类：毒性语言、医学术语、非毒性语言及少数群体相关术语。接着，我们训练了一个基于BERT的毒性语言分类模型，其F1宏值达到0.89。该训练好的模型可直接应用于实际环境，并能作为毒性内容检测系统的组件进行集成。
URL
https://arxiv.org/abs/2604.01745
PDF
-
Bounded Morality: Defining the Space of Moral Computation
2026-04-01 17:35:43Max Kanwal, Caryn Tran, Patrick MineaultAbstract
Moral cognition has traditionally been modeled as adherence to fixed ethical theories--deontology, consequentialism, virtue ethics--implemented as static rules or value functions. We propose Bounded Morality, a formal framework for analyzing the computational demands of moral problems faced by finite agents. Extending Herbert Simon's notion of bounded rationality, we formalize moral situations along two orthogonal dimensions: moral breadth, the scope of entities treated as morally relevant, and moral depth, the inferential integration required to evaluate their interactions. Limited resources impose an unavoidable tradeoff between these dimensions, defining a feasible space of moral computation. Within this space, ethical theories correspond to locally efficient strategies adapted to different demand regimes rather than competing accounts of moral truth. The framework yields a formal notion of moral regret and moral progress under constraint, and implies that moral alignment in artificial systems depends on the scaling and allocation of moral reasoning capacity rather than on direct imitation of human judgments.
Abstract (translated)
URL
https://arxiv.org/abs/2607.00002
PDF
