Knowledge_Graph
-
ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian
2026-03-31 14:32:34Cristian Santini, Sebastian Barzaghi, Paolo Sernani, Emanuele Frontoni, Laura Melosi, Mehwish AlamAbstract
This paper introduces ENEIDE (Extracting Named Entities from Italian Digital Editions), a silver standard dataset for Named Entity Recognition and Linking (NERL) in historical Italian texts. The corpus comprises 2,111 documents with over 8,000 entity annotations semi-automatically extracted from two scholarly digital editions: Digital Zibaldone, the philosophical diary of the Italian poet Giacomo Leopardi (1798--1837), and Aldo Moro Digitale, the complete works of the Italian politician Aldo Moro (1916--1978). Annotations cover multiple entity types (person, location, organization, literary work) linked to Wikidata identifiers, including NIL entities that cannot be mapped to the knowledge graph. To the best of our knowledge, ENEIDE represents the first multi-domain, publicly available NERL dataset for historical Italian with training, development, and test splits. We present a methodology for semi-automatic annotations extraction from manually curated scholarly digital editions, including quality control and annotation enhancement procedures. Baseline experiments using state-of-the-art models demonstrate the dataset's challenge for NERL and the gap between zero-shot approaches and fine-tuned models. The dataset's diachronic coverage spanning two centuries makes it particularly suitable for temporal entity disambiguation and cross-domain evaluation. ENEIDE is released under a CC BY-NC-SA 4.0 license.
Abstract (translated)
本文介绍了ENEIDE（从意大利数字版本文献中提取命名实体），这是一个面向历史意大利语文本的命名实体识别与链接（NERL）银标数据集。该语料库包含2,111篇文档，超过8,000条实体标注，这些标注半自动提取自两部学术数字版本文献：意大利诗人贾科莫·莱奥帕尔迪（1798-1837）的哲学日记《数字扎伊尔博内》（Digital Zibaldone），以及意大利政治家阿尔多·莫罗（1916-1978）的完整作品集《数字阿尔多·莫罗》（Aldo Moro Digitale）。标注涵盖多种实体类型（人物、地点、组织、文学作品），均链接至维基数据标识符，包括无法映射到知识图的NIL实体。据我们所知，ENEIDE是首个面向历史意大利语的多领域公开NERL数据集，包含训练集、开发集和测试集划分。我们提出了一种从人工校对的学术数字版本文献中半自动提取标注的方法论，包括质量控制和标注增强流程。使用先进模型进行的基线实验表明，该数据集对NERL任务具有挑战性，且零样本方法与微调模型之间存在性能差距。该数据集跨越两个世纪的时间覆盖范围，特别适用于时序实体消歧和跨领域评估。ENEIDE以CC BY-NC-SA 4.0许可证发布。
URL
https://arxiv.org/abs/2603.29801
PDF
-
GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
2026-03-30 14:56:59Shuwen Xu, Yao Xu, Jiaxiang Liu, Chenhao Yuan, Wenshuo Peng, Jun Zhao, Kang LiuAbstract
Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reasoning generalization. Specifically, existing approaches often restrict agent exploration: prompting-based methods lack autonomous navigation training, while current training pipelines usually confine reasoning to predefined trajectories. To this end, this paper proposes \textit{GraphWalker}, a novel agentic KGQA framework that addresses these challenges through \textit{Automated Trajectory Synthesis} and \textit{Stage-wise Fine-tuning}. GraphWalker adopts a two-stage SFT training paradigm: First, the agent is trained on structurally diverse trajectories synthesized from constrained random-walk paths, establishing a broad exploration prior over the KG; Second, the agent is further fine-tuned on a small set of expert trajectories to develop reflection and error recovery capabilities. Extensive experiments demonstrate that our stage-wise SFT paradigm unlocks a higher performance ceiling for a lightweight reinforcement learning (RL) stage, enabling GraphWalker to achieve state-of-the-art performance on CWQ and WebQSP. Additional results on GrailQA and our constructed GraphWalkerBench confirm that GraphWalker enhances generalization to out-of-distribution reasoning paths. The code is publicly available at this https URL
Abstract (translated)
智能体知识图谱问答（KGQA）要求智能体与知识图谱（KG）进行迭代交互，面临训练数据稀缺和推理泛化能力不足的双重挑战。具体而言，现有方法常限制智能体的探索能力：基于提示的方法缺乏自主导航训练，而当前训练流程通常将推理局限于预定义轨迹。为此，本文提出一种新型智能体KGQA框架GraphWalker，通过自动化轨迹合成与分阶段微调解决上述挑战。GraphWalker采用两阶段监督微调（SFT）范式：首先，智能体在从受限随机游走路径合成的结构多样化轨迹上进行训练，建立对KG的广泛探索先验；其次，智能体在小规模专家轨迹上进一步微调，发展反思与纠错能力。大量实验表明，我们提出的分阶段SFT范式为轻量级强化学习（RL）阶段释放了更高性能上限，使GraphWalker在CWQ和WebQSP数据集上达到最先进性能。在GrailQA及我们构建的GraphWalkerBench上的额外结果证实，GraphWalker增强了对分布外推理路径的泛化能力。代码已公开于此https URL。
URL
https://arxiv.org/abs/2603.28533
PDF
-
TIEG-Youpu Solution for NeurIPS 2022 WikiKG90Mv2-LSC
2026-03-30 14:45:30Feng Nie, Zhixiu Ye, Sifa Xie, Shuang Wu, Xin Yuan, Liang Yao, Jiazhen Peng, Xu ChengAbstract
WikiKG90Mv2 in NeurIPS 2022 is a large encyclopedic knowledge graph. Embedding knowledge graphs into continuous vector spaces is important for many practical applications, such as knowledge acquisition, question answering, and recommendation systems. Compared to existing knowledge graphs, WikiKG90Mv2 is a large scale knowledge graph, which is composed of more than 90 millions of entities. Both efficiency and accuracy should be considered when building graph embedding models for knowledge graph at scale. To this end, we follow the retrieve then re-rank pipeline, and make novel modifications in both retrieval and re-ranking stage. Specifically, we propose a priority infilling retrieval model to obtain candidates that are structurally and semantically similar. Then we propose an ensemble based re-ranking model with neighbor enhanced representations to produce final link prediction results among retrieved candidates. Experimental results show that our proposed method outperforms existing baseline methods and improves MRR of validation set from 0.2342 to 0.2839.
Abstract (translated)
URL
https://arxiv.org/abs/2603.28512
PDF
-
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
2026-03-30 14:40:58Jos\'e Guilherme Marques dos Santos, Ricardo Yang, Rui Humberto Pereira, Alexandre Sousa, Br\'igida M\'onica Faria, Henrique Lopes Cardoso, Jos\'e Duarte, Jos\'e Lu\'is Reis, Lu\'is Paulo Reis, Pedro Pimenta, Jos\'e Paulo Marques dos SantosAbstract
Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy. We address this gap through a systematic comparison of four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 19 pipeline configurations for extracting text and other contents from PDFs, varying the conversion tool, cleaning transformations, splitting strategy, and metadata enrichment. Evaluation was performed using a manually curated 50-question benchmark over a corpus of 36 Portuguese administrative documents (1,706 pages, ~492K words), with LLM-as-judge scoring averaged over 10 runs. Two baselines bounded the results: naïve PDFLoader (86.9%) and manually curated Markdown (97.1%). Docling with hierarchical splitting and image descriptions achieved the highest automated accuracy (94.1%). Metadata enrichment and hierarchy-aware chunking contributed more to accuracy than the conversion framework choice alone. Font-based hierarchy rebuilding consistently outperformed LLM-based approaches. An exploratory GraphRAG implementation scored only 82%, underperforming basic RAG, suggesting that naïve knowledge graph construction without ontological guidance does not yet justify its added complexity. These findings demonstrate that data preparation quality is the dominant factor in RAG system performance.
Abstract (translated)
检索增强生成（RAG）系统的性能高度依赖于文档预处理的质量，然而此前尚无研究通过评估下游问答准确率来比较PDF处理框架。本研究通过系统对比四个开源PDF转Markdown转换框架（Docling、MinerU、Marker和DeepSeek OCR），在19种流水线配置下从PDF中提取文本及其他内容，涵盖转换工具、清洗转换、切分策略和元数据增强四个变量。评估基于手动构建的50道问题基准测试，针对36份葡萄牙行政文件（共1,706页，约49.2万字）的语料库进行，采用LLM作为评判者并取10次运行的平均分。两个基线限定了结果范围：朴素PDFLoader（86.9%）与手动整理的Markdown（97.1%）。采用分层切分和图像描述的Docling实现了最高的自动化准确率（94.1%）。元数据增强与分层感知的文本切分对准确率的提升贡献大于转换框架本身的选择。基于字体的层级重建方法持续优于基于LLM的方法。探索性GraphRAG实现仅得82分，表现低于基础RAG，表明缺乏本体论指导的朴素知识图谱构建尚未证明其额外复杂性的合理性。这些发现证明，数据准备质量是决定RAG系统性能的主导因素。
URL
https://arxiv.org/abs/2604.04948
PDF
-
Building evidence-based knowledge graphs from full-text literature for disease-specific biomedical reasoning
2026-03-30 11:53:45Chang Zong, Sicheng Lv, Si-tu Xue, Huilin Zheng, Jian Wan, Lei ZhangAbstract
Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat triples that omit study design, provenance, and quantitative support. Here we present EvidenceNet, a framework and dataset for building disease-specific knowledge graphs from full-text biomedical literature. EvidenceNet uses a large language model (LLM)-assisted pipeline to extract experimentally grounded findings as structured evidence nodes, normalize biomedical entities, score evidence quality, and connect evidence records through typed semantic relations. We release two resources: EvidenceNet-HCC with 7,872 evidence records, 10,328 graph nodes, and 49,756 edges, and EvidenceNet-CRC with 6,622 records, 8,795 nodes, and 39,361 edges. Technical validation shows high component fidelity, including 98.3% field-level extraction accuracy, 100.0% high-confidence entity-link accuracy, 87.5% fusion integrity, and 90.0% semantic relation-type accuracy. In downstream evaluation, EvidenceNet improves internal and external retrieval-augmented question answering and retains structural signal for future link prediction and target prioritization. These results establish EvidenceNet as a disease-specific resource for evidence-aware biomedical reasoning and hypothesis generation.
Abstract (translated)
生物医学知识资源通常要么以非结构化文本形式保留证据，要么将其压缩为省略了研究设计、来源和定量支持的扁平三元组。在此，我们提出EvidenceNet，一个用于从生物医学全文文献中构建疾病特定知识图谱的框架和数据集。EvidenceNet采用大语言模型辅助的流程，将实验性发现提取为结构化证据节点，规范化生物医学实体，评估证据质量，并通过类型化语义关系连接证据记录。我们发布了两项资源：包含7,872条证据记录、10,328个图谱节点和49,756条边的EvidenceNet-HCC，以及包含6,622条记录、8,795个节点和39,361条边的EvidenceNet-CRC。技术验证显示高组件保真度，包括98.3%的字段级提取准确率、100.0%的高置信度实体链接准确率、87.5%的融合完整性以及90.0%的语义关系类型准确率。在下游评估中，EvidenceNet提升了内部和外部检索增强问答的表现，并为未来链接预测和靶点优先级排序保留了结构信号。这些结果确立了EvidenceNet作为面向证据感知的生物医学推理与假设生成的疾病特定资源。
URL
https://arxiv.org/abs/2603.28325
PDF
-
GEAKG: Generative Executable Algorithm Knowledge Graphs
2026-03-30 00:42:48Camilo Chac\'on Sartori, Jos\'e H. Garc\'ia, Andrei Voicu Tomut, Christian BlumAbstract
In the context of algorithms for problem solving, procedural knowledge -- the know-how of algorithm design and operator composition -- remains implicit in code, lost between runs, and must be re-engineered for each new domain. Knowledge graphs (KGs) have proven effective for organizing declarative knowledge, yet current KG paradigms provide limited support for representing procedural knowledge as executable, learnable graph structures. We introduce \textit{Generative Executable Algorithm Knowledge Graphs} (GEAKG), a class of KGs whose nodes store executable operators, whose edges encode learned composition patterns, and whose traversal generates solutions. A GEAKG is \emph{generative} (topology and operators are synthesized by a Large Language Model), \emph{executable} (every node is runnable code), and \emph{transferable} (learned patterns generalize zero-shot across domains). The framework is domain-agnostic at the engine level: the same three-layer architecture and Ant Colony Optimization (ACO)-based learning engine can be instantiated across domains, parameterized by a pluggable ontology (\texttt{RoleSchema}). Two case studies -- sharing no domain-specific framework code -- provide concrete evidence for this framework hypothesis: (1)~Neural Architecture Search across 70 cross-dataset transfer pairs on two tabular benchmarks, and (2)~Combinatorial Optimization, where knowledge learned on the Traveling Salesman Problem transfers zero-shot to scheduling and assignment domains. Taken together, the results support that algorithmic expertise can be explicitly represented, learned, and transferred as executable knowledge graphs.
Abstract (translated)
在问题求解算法的背景下，过程性知识——即算法设计与操作符组合的实操技能——仍隐含在代码中，在运行间丢失，且必须为每个新领域重新设计。知识图谱（KGs）已被证明能有效组织陈述性知识，但当前KG范式在将过程性知识表示为可执行、可学习的图结构方面支持有限。我们提出了\textit{生成式可执行算法知识图谱}（GEAKG），这是一类KG，其节点存储可执行操作符，边编码习得的组合模式，遍历即可生成解决方案。GEAKG是\textit{生成式}的（拓扑结构与操作符由大语言模型合成）、\textit{可执行}的（每个节点均为可运行代码）且\textit{可迁移}的（习得模式能跨领域零样本泛化）。该框架在引擎层面是领域无关的：相同的三层架构与基于蚁群优化（ACO）的学习引擎可实例化于不同领域，通过可插拔的本体（\texttt{RoleSchema}）进行参数化。两项不共享任何领域特定框架代码的案例研究为该框架假设提供了具体证据：(1) 在两个表格基准测试上进行的跨70个数据集迁移配对的神经架构搜索，以及(2) 组合优化，其中在旅行商问题上学到的知识可零样本迁移至调度与分配领域。综合而言，这些结果支持了算法专长可被显式表示为可执行知识图谱、从中学习并实现迁移的结论。
URL
https://arxiv.org/abs/2603.27922
PDF
-
GAAMA: Graph Augmented Associative Memory for Agents
2026-03-29 23:33:38Swarna Kamal Paul, Shubhendu Sharma, Nitin SareenAbstract
AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural relationships between memories, or use memory compression and vector retrieval that cannot capture the associative structure of multi-session conversations. There are few graph based techniques proposed in the literature, however they still suffer from hub dominated retrieval and poor hierarchical reasoning over evolving memory. We propose GAAMA, a graph-augmented associative memory system that constructs a concept-mediated hierarchical knowledge graph through a three-step pipeline: (1)~verbatim episode preservation from raw conversations, (2)~LLM-based extraction of atomic facts and topic-level concept nodes, and (3)~synthesis of higher-order reflections. The resulting graph uses four node types (episode, fact, reflection, concept) connected by five structural edge types, with concept nodes providing cross-cutting traversal paths that complement semantic similarity. Retrieval combines cosine-similarity-based $k$-nearest neighbor search with edge-type-aware Personalized PageRank (PPR) through an additive scoring function. On the LoCoMo-10 benchmark (1,540 questions across 10 multi-session conversations), GAAMA achieves 78.9\% mean reward, outperforming a tuned RAG baseline (75.0\%), HippoRAG (69.9\%), A-Mem (47.2\%), and Nemori (52.1\%). Ablation analysis shows that augmenting graph-traversal-based ranking (Personalized PageRank) with semantic search consistently improves over pure semantic search on graph nodes (+1.0 percentage point overall).
Abstract (translated)
在多轮会话中与用户交互的AI代理需要持久的长期记忆来维持连贯且个性化的行为。当前方法要么依赖扁平化的检索增强生成（RAG），该方法会丢失记忆间的结构关系；要么使用记忆压缩和向量检索，无法捕捉多轮会话对话中的联想结构。文献中虽提出了一些基于图的技术，但仍受限于中心节点主导的检索以及对动态演化记忆的层次化推理能力不足。我们提出GAAMA，一个图增强联想记忆系统，它通过三步流水线构建概念介导的层次化知识图谱：(1) 从原始对话中逐字保留情景片段，(2) 基于大语言模型提取原子事实和主题级概念节点，(3) 合成高阶反思。生成的图谱包含四种节点类型（情景片段、事实、反思、概念），通过五种结构边类型连接，其中概念节点提供跨主题的遍历路径，以补充语义相似性。检索通过加性评分函数，将基于余弦相似度的k近邻搜索与考虑边类型感知的个性化PageRank（PPR）相结合。在LoCoMo-10基准测试（涵盖10轮多会话对话的1540个问题）中，GAAMA达到78.9%的平均奖励，优于调优后的RAG基线（75.0%）、HippoRAG（69.9%）、A-Mem（47.2%）和Nemori（52.1%）。消融分析表明，在语义搜索基础上增加基于图遍历的排序（个性化PageRank）始终优于仅对图谱节点进行纯语义搜索（整体提升1.0个百分点）。
URL
https://arxiv.org/abs/2603.27910
PDF
-
TailNLG: A Multilingual Benchmark Addressing Verbalization of Long-Tail Entities
2026-03-29 17:01:54Lia Draetta, Michael Oliverio, Virginia Ram\'on-Ferrer, Pier Felice Balestrucci, Flaviana Corallo, Carlos Badenes-Olmedo, Alessandro Mazzei, Marco Antonio Stranisci, Rossana DamianoAbstract
The automatic verbalization of structured knowledge is a key task for making knowledge graphs accessible to non-expert users and supporting retrieval-augmented generation systems. Although recent advances in Data-to-Text generation have improved multilingual coverage, little attention has been paid to potential biases in the verbalization of rare entities, frequently known as long-tail entities. In this work, we present the first systematic study of long-tail entities in Data-to-Text generation. We introduce TailNLG, a new multilingual benchmark in English, Italian, and Spanish, built from Wikidata and covering entities with varying levels of popularity. We evaluate three different families of large language models in zero-shot settings and compare their performance on rare versus common entities, as well as against the established WebNLG benchmark. Our results reveal a consistent bias against long-tail entities: embedding-based scores are lower, and model uncertainty is higher for rare entities. We further show that the impact of long-tail entities varies across models and languages, and that existing evaluation metrics do not consistently capture these differences, highlighting the need for more reliable evaluation frameworks.
Abstract (translated)
结构化知识的自动叙述化是让非专业用户访问知识图谱并支持检索增强生成系统的关键任务。尽管近期数据到文本生成技术的进步提升了多语言覆盖范围，但针对稀有实体（通常称为长尾实体）叙述化中潜在偏差的研究尚未受到足够关注。本研究首次系统性地探讨了数据到文本生成中的长尾实体问题。我们提出了TailNLG——一个基于维基数据构建的新的多语言基准测试集，涵盖英语、意大利语和西班牙语，并包含不同流行度级别的实体。我们在零样本设置下评估了三类大型语言模型，比较了它们在稀有与常见实体上的表现，并与成熟的WebNLG基准测试进行了对比。研究结果揭示了针对长尾实体的持续性偏差：稀有实体的基于嵌入的评分更低，模型不确定性更高。我们还发现长尾实体的影响因模型和语言而异，且现有评估指标未能一致捕捉这些差异，这凸显了建立更可靠评估框架的必要性。
URL
https://arxiv.org/abs/2603.27768
PDF
-
Transferring Physical Priors into Remote Sensing Segmentation via Large Language Models
2026-03-29 03:55:11Yuxi Lu, Kunqi Li, Zhidong Li, Xiaohan Su, Biao Wu, Chenya Huang, Bin LiangAbstract
Semantic segmentation of remote sensing imagery is fundamental to Earth observation. Achieving accurate results requires integrating not only optical images but also physical variables such as the Digital Elevation Model (DEM), Synthetic Aperture Radar (SAR) and Normalized Difference Vegetation Index (NDVI). Recent foundation models (FMs) leverage pre-training to exploit these variables but still depend on spatially aligned data and costly retraining when involving new sensors. To overcome these limitations, we introduce a novel paradigm for integrating domain-specific physical priors into segmentation models. We first construct a Physical-Centric Knowledge Graph (PCKG) by prompting large language models to extract physical priors from 1,763 vocabularies, and use it to build a heterogeneous, spatial-aligned dataset, Phy-Sky-SA. Building on this foundation, we develop PriorSeg, a physics-aware residual refinement model trained with a joint visual-physical strategy that incorporates a novel physics-consistency loss. Experiments on heterogeneous settings demonstrate that PriorSeg improves segmentation accuracy and physical plausibility without retraining the FMs. Ablation studies verify the effectiveness of the Phy-Sky-SA dataset, the PCKG, and the physics-consistency loss.
Abstract (translated)
URL
https://arxiv.org/abs/2603.27504
PDF
-
Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
2026-03-28 14:18:12Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler, Elias Gr\"unewald, Felix BalzerAbstract
Large Language Model (LLM) coding agents typically explore codebases through repeated file-reading and grep-searching, consuming thousands of tokens per query without structural understanding. We present Codebase-Memory, an open-source system that constructs a persistent, Tree-Sitter-based knowledge graph via the Model Context Protocol (MCP), parsing 66 languages through a multi-phase pipeline with parallel worker pools, call-graph traversal, impact analysis, and community discovery. Evaluated across 31 real-world repositories, Codebase-Memory achieves 83% answer quality versus 92% for a file-exploration agent, at ten times fewer tokens and 2.1 times fewer tool calls. For graph-native queries such as hub detection and caller ranking, it matches or exceeds the explorer on 19 of 31 languages.
Abstract (translated)
大型语言模型（LLM）编码代理通常通过重复的文件读取和grep搜索来探索代码库，每次查询消耗数千个token却缺乏结构理解。我们提出Codebase-Memory，一个开源系统，它通过模型上下文协议（MCP）构建持久化的、基于Tree-Sitter的知识图谱，采用多阶段流水线并行工作池、调用图遍历、影响分析和社区发现来解析66种语言。在31个真实仓库的评估中，Codebase-Memory达到83%的答案质量，而文件探索代理为92%，但前者仅使用十分之一的token和2.1倍更少的工具调用。对于中心节点检测和调用者排名等图原生查询，它在31种语言中的19种上表现匹配或超过探索代理。
URL
https://arxiv.org/abs/2603.27277
PDF
-
Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization
2026-03-27 10:38:40Ziqiao Kong, Wanxu Xia, Chong Wang, Yi Lu, Pan Li, Shaohua Li, Zong Cao, Yang LiuAbstract
Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic. We observe that recurring vulnerabilities across diverse DeFi business models often share the same underlying economic mechanisms, which we term DeFi semantics, and that capturing these shared abstractions can enable more systematic auditing. Building on this insight, we propose Knowdit, a knowledge-driven, agentic framework for smart contract vulnerability detection. Knowdit first constructs an auditing knowledge graph from historical human audit reports, linking fine-grained DeFi semantics with recurring vulnerability patterns. Given a new project, a multi-agent framework leverages this knowledge through an iterative loop of specification generation, harness synthesis, fuzz execution, and finding reflection, driven by a shared working memory for continuous refinement. We evaluate Knowdit on 12 recent Code4rena projects with 75 ground-truth vulnerabilities. Knowdit detects all 14 high-severity and 77\% of medium-severity vulnerabilities with only 2 false positives, significantly outperforming all baselines. Applied to six real-world projects, Knowdit further discovers 12 high- and 10 medium-severity previously unknown vulnerabilities, proving its outstanding performance.
Abstract (translated)
智能合约管理着去中心化金融(DeFi)中数十亿美元的资金，然而自动化漏洞检测仍极具挑战性，因为许多漏洞与项目特定的业务逻辑紧密耦合。我们观察到，不同DeFi业务模型中反复出现的漏洞往往共享相同的基础经济机制，我们将其称为DeFi语义，且捕捉这些共享抽象概念能够实现更系统化的审计。基于这一洞察，我们提出了Knowdit——一个知识驱动的智能体框架，用于智能合约漏洞检测。Knowdit首先从历史人工审计报告中构建审计知识图谱，将细粒度的DeFi语义与反复出现的漏洞模式相关联。对于新项目，多智能体框架通过共享工作记忆驱动的迭代循环——包括规范生成、harness合成、模糊测试执行与发现反思——来利用这些知识进行持续优化。我们在12个近期Code4rena项目（含75个真实漏洞）上评估Knowdit，其检测到全部14个高危漏洞及77%的中危漏洞，仅产生2个误报，显著优于所有基线方法。应用于六个真实项目时，Knowdit进一步发现了12个高危和10个中危的先前未知漏洞，证明了其卓越性能。
URL
https://arxiv.org/abs/2603.26270
PDF
-
Semi-Automated Knowledge Engineering and Process Mapping for Total Airport Management
2026-03-27 05:07:58Darryl Teo, Adharsha Sam, Chuan Shen Marcus Koh, Rakesh Nagi, Nuno Antunes RibeiroAbstract
Documentation of airport operations is inherently complex due to extensive technical terminology, rigorous regulations, proprietary regional information, and fragmented communication across multiple stakeholders. The resulting data silos and semantic inconsistencies present a significant impediment to the Total Airport Management (TAM) initiative. This paper presents a methodological framework for constructing a domain-grounded, machine-readable Knowledge Graph (KG) through a dual-stage fusion of symbolic Knowledge Engineering (KE) and generative Large Language Models (LLMs). The framework employs a scaffolded fusion strategy in which expert-curated KE structures guide LLM prompts to facilitate the discovery of semantically aligned knowledge triples. We evaluate this methodology on the Google LangExtract library and investigate the impact of context window utilization by comparing localized segment-based inference with document-level processing. Contrary to prior empirical observations of long-context degradation in LLMs, document-level processing improves the recovery of non-linear procedural dependencies. To ensure the high-fidelity provenance required in airport operations, the proposed framework fuses a probabilistic model for discovery and a deterministic algorithm for anchoring every extraction to its ground source. This ensures absolute traceability and verifiability, bridging the gap between "black-box" generative outputs and the transparency required for operational tooling. Finally, we introduce an automated framework that operationalizes this pipeline to synthesize complex operational workflows from unstructured textual corpora.
Abstract (translated)
机场运营文档的编制具有内在复杂性，这源于其广泛的技术术语、严格的法规体系、专有的区域信息以及跨多方利益相关者的分散化沟通。由此产生的数据孤岛与语义不一致现象，对全域机场管理（TAM）倡议构成了重大障碍。本文提出了一种方法论框架，通过符号知识工程（KE）与生成式大语言模型（LLMs）的双阶段融合，构建基于领域 grounded 的可机器读取知识图谱（KG）。该框架采用支架式融合策略，由专家策划的KE结构指导LLM提示词，以促进语义对齐的知识三元组发现。我们在Google LangExtract库上评估了该方法，并通过对比基于本地化片段的推理与文档级处理，研究了上下文窗口利用的影响。与之前关于LLM长上下文性能衰减的实证观察相反，文档级处理改善了非线性程序依赖关系的恢复。为确保机场运营所需的高保真溯源，所提框架融合了概率发现模型与确定性算法，将每次提取锚定至其原始数据源。这确保了绝对的可追溯性与可验证性，弥合了"黑箱"生成式输出与运营工具所需透明度之间的差距。最后，我们引入了一个自动化框架，将这一流程操作化，从而从非结构化文本语料库中综合复杂运营工作流。
URL
https://arxiv.org/abs/2603.26076
PDF
-
Do Neurons Dream of Primitive Operators? Wake-Sleep Compression Rediscovers Schank's Event Semantics
Abstract
We show that they do. Schank's conceptual dependency theory proposed that all events decompose into primitive operations -- ATRANS, PTRANS, MTRANS, and others -- hand-coded from linguistic intuition. Can the same primitives be discovered automatically through compression pressure alone? We adapt DreamCoder's wake-sleep library learning to event state transformations. Given events as before/after world state pairs, our system finds operator compositions explaining each event (wake), then extracts recurring patterns as new operators optimized under Minimum Description Length (sleep). Starting from four generic primitives, it discovers operators mapping directly to Schank's: MOVE_PROP_has = ATRANS, CHANGE_location = PTRANS, SET_knows = MTRANS, SET_consumed = INGEST, plus compound operators ("mail" = ATRANS + PTRANS) and novel emotional state operators absent from Schank's taxonomy. We validate on synthetic events and real-world commonsense data from the ATOMIC knowledge graph. On synthetic data, discovered operators achieve Bayesian MDL within 4% of Schank's hand-coded primitives while explaining 100% of events vs. Schank's 81%. On ATOMIC, results are more dramatic: Schank's primitives explain only 10% of naturalistic events, while the discovered library explains 100%. Dominant operators are not physical-action primitives but mental and emotional state changes -- CHANGE_wants (20%), CHANGE_feels (18%), CHANGE_is (18%) -- none in Schank's original taxonomy. These results provide the first empirical evidence that event primitives can be derived from compression pressure, that Schank's core primitives are information-theoretically justified, and that the complete inventory is substantially richer than proposed -- with mental/emotional operators dominating in naturalistic data.
Abstract (translated)
我们证明了它们确实可以。尚克的概念依赖理论提出所有事件都可分解为原语操作——如ATRANS、PTRANS、MTRANS等——这些操作基于语言学直觉手工编码。能否仅通过压缩压力自动发现相同的原语？我们改编了DreamCoder的唤醒-睡眠库学习机制用于事件状态转换。给定事件的前后世界状态对，我们的系统先为每个事件寻找解释性算子组合（唤醒阶段），再提取重复模式作为新算子，并在最小描述长度原则下进行优化（睡眠阶段）。从四个通用原语出发，系统发现了与尚克原语直接对应的算子：MOVE_PROP_has = ATRANS，CHANGE_location = PTRANS，SET_knows = MTRANS，SET_consumed = INGEST，同时还发现了复合算子（如"mail" = ATRANS + PTRANS）以及尚克分类中缺失的情感状态算子。我们在合成事件和ATOMIC知识图谱的真实常识数据上进行了验证。在合成数据上，发现的算子在贝叶斯MDL指标上仅与尚克手工原语相差4%，却能解释100%的事件（尚克原语仅解释81%）。在ATOMIC数据上结果更为显著：尚克原语仅能解释10%的自然事件，而发现的算子库实现了100%解释。主导算子并非物理动作原语，而是心理与情感状态变化——CHANGE_wants（20%）、CHANGE_feels（18%）、CHANGE_is（18%）——这些均未出现在尚克原始分类中。这些结果首次提供实证证据：事件原语可从压缩压力中推导，尚克核心原语具有信息论依据，且完整原语库比原设想更为丰富——在自然数据中，心理/情感算子占据主导地位。
URL
https://arxiv.org/abs/2603.25975
PDF
-
Methods for Knowledge Graph Construction from Text Collections: Development and Applications
2026-03-26 19:36:00Vanni ZavarellaAbstract
Virtually every sector of society is experiencing a dramatic growth in the volume of unstructured textual data that is generated and published, from news and social media online interactions, through open access scholarly communications and observational data in the form of digital health records and online drug reviews. The volume and variety of data across all this range of domains has created both unprecedented opportunities and pressing challenges for extracting actionable knowledge for several application scenarios. However, the extraction of rich semantic knowledge demands the deployment of scalable and flexible automatic methods adaptable across text genres and schema specifications. Moreover, the full potential of these data can only be unlocked by coupling information extraction methods with Semantic Web techniques for the construction of full-fledged Knowledge Graphs, that are semantically transparent, explainable by design and interoperable. In this thesis, we experiment with the application of Natural Language Processing, Machine Learning and Generative AI methods, powered by Semantic Web best practices, to the automatic construction of Knowledge Graphs from large text corpora, in three use case applications: the analysis of the Digital Transformation discourse in the global news and social media platforms; the mapping and trend analysis of recent research in the Architecture, Engineering, Construction and Operations domain from a large corpus of publications; the generation of causal relation graphs of biomedical entities from electronic health records and patient-authored drug reviews. The contributions of this thesis to the research community are in terms of benchmark evaluation results, the design of customized algorithms and the creation of data resources in the form of Knowledge Graphs, together with data analysis results built on top of them.
Abstract (translated)
社会几乎所有领域都正在经历非结构化文本数据量的大幅增长，这些数据从新闻和社交媒体在线互动中产生并发布，涵盖开放获取的学术交流、数字健康记录形式的观测数据以及患者撰写的药物评论。跨领域数据的庞大规模与多样性，为多个应用场景提取可操作知识带来了前所未有的机遇与紧迫挑战。然而，要提取丰富的语义知识，需要部署可扩展、灵活且能适应不同文本体裁与模式规范的自动方法。此外，这些数据的全部潜力唯有通过将信息提取方法与语义网技术相结合，构建出语义透明、可解释设计且可互操作的全功能知识图谱，才能得以释放。在本论文中，我们依托语义网最佳实践，实验性地将自然语言处理、机器学习与生成式人工智能方法应用于从大规模文本语料库自动构建知识图谱，具体包括三个应用案例：基于全球新闻与社交媒体平台分析数字化转型议题；从大量出版物中绘制并趋势分析建筑、工程、施工与运营领域的最新研究；从电子健康记录与患者撰写的药物评论中生成生物医学实体的因果关系图谱。本论文对研究界的贡献体现在基准评估结果、定制化算法设计以及以知识图谱形式创建的数据资源，并基于这些资源产出数据分析结果。
URL
https://arxiv.org/abs/2603.25862
PDF
-
GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
2026-03-26 01:30:22Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li, Tao Sheng, Sujith Ravi, Dan RothAbstract
Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources. Prior approaches to this problem include agentic retrieval strategies, which expand the semantic search space by generating additional queries. However, these methods do not fully leverage the organizational structure of the data and instead rely on iterative exploration, which can lead to inefficient retrieval. Another class of approaches employs knowledge graphs to model non-semantic relationships through graph edges. Although effective in capturing richer proximities, such methods incur significant maintenance costs and are often incompatible with the vector stores used in most production systems. To address these limitations, we propose GraphER, a graph-based enrichment and reranking method that captures multiple forms of proximity beyond semantic similarity. GraphER independently enriches data objects during offline indexing and performs graph-based reranking over candidate objects at query time. This design does not require a knowledge graph, allowing GraphER to integrate seamlessly with standard vector stores. In addition, GraphER is retriever-agnostic and introduces negligible latency overhead. Experiments on multiple retrieval benchmarks demonstrate the effectiveness of the proposed approach.
Abstract (translated)
在检索增强生成（RAG）系统中，语义搜索往往不足以满足复杂的信息需求，尤其是当相关证据分散于多个来源时。针对这一问题，既往方法包括采用智能检索策略，通过生成额外查询来扩展语义搜索空间。然而，这些方法未能充分利用数据的组织结构，而是依赖迭代探索，可能导致检索效率低下。另一类方法则利用知识图谱，通过图边建模非语义关系。尽管此类方法能有效捕捉更丰富的邻近性，但维护成本高昂，且常与大多数生产系统中使用的向量存储不兼容。为应对上述局限，本文提出GraphER——一种基于图的丰富与重排序方法，可捕捉语义相似性之外的多重邻近性。GraphER在离线索引阶段独立丰富数据对象，并在查询时对候选对象执行基于图的重排序。该设计无需知识图谱，使GraphER能够与标准向量存储无缝集成。此外，GraphER与检索器无关，且引入的延迟开销可忽略不计。多项检索基准实验验证了所提方法的有效性。
URL
https://arxiv.org/abs/2603.24925
PDF
-
AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
2026-03-25 15:16:51Yunbo LongAbstract
Existing automated research systems operate as stateless, linear pipelines, generating outputs without maintaining a persistent understanding of the research landscape. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify or refine each other's findings. We present AutoProf (Autonomous Professor), a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests, from literature review through gap discovery, method development, evaluation, and paper writing, via autonomous exploration and self-correcting updates. Unlike sequential pipelines, AutoProf maintains a continuously evolving Research World Model implemented as a Knowledge Graph, capturing methods, benchmarks, limitations, and unexplored gaps as shared memory across agents. The framework introduces three contributions: first, structured gap discovery that decomposes methods into modules, evaluates them across benchmarks, and identifies module-level gaps; second, self-correcting discovery loops that analyze why modules succeed or fail, detect benchmark biases, and assess evaluation adequacy; third, self-improving development loops using cross-domain mechanism search to iteratively address failing components. All agents operate under a consensus mechanism where findings are validated before being committed to the shared model. The framework is model-agnostic, supports mainstream large language models, and scales elastically with token budget from lightweight exploration to full-scale investigation.
Abstract (translated)
现有自动化研究系统作为无状态线性流水线运行，生成输出时无法维持对研究领域的持续理解。它们按顺序处理论文，提出缺乏结构化空白分析的想法，且缺乏让智能体验证或修正彼此发现的机制。我们提出AutoProf（自主教授），一个多智能体编排框架，其中专业化智能体提供端到端的AI研究监督，由人类兴趣驱动，覆盖从文献综述、空白发现、方法开发、评估到论文写作的全流程，通过自主探索和自我修正更新实现。与顺序流水线不同，AutoProf维护一个持续演进的研究世界模型（以知识图谱实现），将方法、基准、局限性和未探索空白作为跨智能体的共享记忆进行捕获。该框架提出三项贡献：一是结构化空白发现，将方法分解为模块，跨基准评估并识别模块级空白；二是自我修正发现循环，分析模块成败原因、检测基准偏差并评估评估充分性；三是自我改进开发循环，利用跨领域机制搜索迭代解决失败组件。所有智能体在共识机制下运行，发现需经验证方可提交至共享模型。该框架与模型无关，支持主流大语言模型，并能根据令牌预算从轻量级探索弹性扩展至全面调查。
URL
https://arxiv.org/abs/2603.24402
PDF
-
Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning
2026-03-25 08:41:32Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov, Dmitry Yudin, Aleksandr PanovAbstract
This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The method augments egocentric vision with an online 3D scene graph that grounds open-vocabulary detections into a metric, relational representation. A dynamic-relation mechanism updates spatial, containment, and affordance edges at every step, and a graph neural encoder is trained end-to-end through the RL objective so that relational features are shaped directly by control performance. Multiple observation modalities (visual, proprioceptive, linguistic, and graph-based) are encoded into a shared latent space, upon which the RL agent operates to drive the control loop. The policy conditions on lightweight graph queries alongside visual and proprioceptive inputs, yielding a compact, semantically informed state for decision making. Experiments on a suite of manipulation tasks with occlusions, distractors, and layout shifts demonstrate consistent gains over strong baselines: the knowledge-conditioned agent achieves higher success rates, improved sample efficiency, and stronger generalization to novel objects and unseen scene configurations. These results support the premise that structured, continuously maintained world knowledge is a powerful inductive bias for scalable, generalizable manipulation: when the knowledge module participates in the RL computation graph, relational representations align with control, enabling robust long-horizon behavior under partial observability.
Abstract (translated)
本文提出了一种基于知识图谱的大规模多任务模型策略优化方法（KG-M3PO），这是一种用于部分可观测环境下多任务机器人操作的框架，统一了感知、知识与策略。该方法通过在线三维场景图增强自我中心视觉，将开放词汇检测结果锚定到度量化的关系表示中。动态关系机制在每一步更新空间、包含与可供性边，图神经编码器通过强化学习目标进行端到端训练，使关系特征直接受控于控制性能。视觉、本体感知、语言及基于图的多种观测模态被编码至共享潜在空间，强化学习智能体在此空间运作以驱动控制循环。策略以轻量级图查询结合视觉与本体感知输入作为条件，生成紧凑且富含语义信息的状态以支持决策。在一系列包含遮挡、干扰物及布局变化的操作任务实验中，该方法相较于强基线持续取得优势：知识条件智能体实现了更高成功率、更优样本效率，以及对新颖物体与未见场景配置的更强泛化能力。这些结果印证了核心观点：结构化且持续维护的世界知识是构建可扩展、可泛化操作能力的强大归纳偏置——当知识模块参与强化学习计算图时，关系表征与控制目标对齐，从而在部分可观测条件下实现鲁棒的长期行为。
URL
https://arxiv.org/abs/2603.24083
PDF
-
GRMLR: Knowledge-Enhanced Small-Data Learning for Deep-Sea Cold Seep Stage Inference
2026-03-25 05:46:59Chenxu Zhou, Zelin Liu, Rui Cai, Houlin Gong, Yikang Yu, Jia Zeng, Yanru Pei, Liang Zhang, Weishu Zhao, Xiaofeng GaoAbstract
Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and more cost-effective alternative, reliable inference remains challenging because the available deep-sea dataset is extremely small ($n = 13$) relative to the microbial feature dimension ($p = 26$), making purely data-driven models highly prone to overfitting. To address this, we propose a knowledge-enhanced classification framework that incorporates an ecological knowledge graph as a structural prior. By fusing macro-microbe coupling and microbial co-occurrence patterns, the framework internalizes established ecological logic into a \underline{\textbf{G}}raph-\underline{\textbf{R}}egularized \underline{\textbf{M}}ultinomial \underline{\textbf{L}}ogistic \underline{\textbf{R}}egression (GRMLR) model, effectively constraining the feature space through a manifold penalty to ensure biologically consistent classification. Importantly, the framework removes the need for macrofauna observations at inference time: macro-microbe associations are used only to guide training, whereas prediction relies solely on microbial abundance profiles. Experimental results demonstrate that our approach significantly outperforms standard baselines, highlighting its potential as a robust and scalable framework for deep-sea ecological assessment.
Abstract (translated)
深海冷泉阶段评估传统上依赖成本高昂、高风险的有载人潜水器作业及大型动物视觉调查。尽管微生物群落提供了一种前景广阔且更具成本效益的替代方案，但由于现有深海数据集规模极小（n=13）而微生物特征维度较高（p=26），纯数据驱动模型极易出现过拟合，导致可靠推断仍具挑战性。为此，我们提出一种融合生态知识图谱作为结构先验的知识增强分类框架。该框架通过整合宏生物-微生物耦合关系与微生物共现模式，将既定生态逻辑内化至图正则多项逻辑回归（GRMLR）模型中，借助流形惩罚有效约束特征空间，确保分类结果符合生物学一致性。重要的是，该框架在推理阶段无需宏生物观测数据：宏生物-微生物关联仅用于指导训练，而预测完全依赖微生物丰度谱。实验结果表明，本方法显著优于标准基线方法，凸显其作为稳健可扩展的深海生态评估框架的潜力。
URL
https://arxiv.org/abs/2603.23961
PDF
-
HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
2026-03-24 12:35:10Devvrat Joshi, Islem RekikAbstract
Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical nature of scientific knowledge. While general-purpose large language models (LLMs) offer adaptability, they are computationally expensive and yield inconsistent accuracy on specialized tasks. As a result, current KGs are shallow and inconsistent, limiting their utility for exploration and synthesis. We propose a two-stage framework for scalable, zero-shot scientific KG construction. The first stage, Z-NERD, introduces (i) Orthogonal Semantic Decomposition (OSD), which promotes domain-agnostic entity recognition by isolating semantic "turns" in text, and (ii) a Multi-Scale TCQK attention mechanism that captures coherent multi-word entities through n-gram-aware attention heads. The second stage, HGNet, performs relation extraction with hierarchy-aware message passing, explicitly modeling parent, child, and peer relations. To enforce global consistency, we introduce two complementary objectives: a Differentiable Hierarchy Loss to discourage cycles and shortcut edges, and a Continuum Abstraction Field (CAF) Loss that embeds abstraction levels along a learnable axis in Euclidean space. This is the first approach to formalize hierarchical abstraction as a continuous property within standard Euclidean embeddings, offering a simpler alternative to hyperbolic methods. We release SPHERE (this https URL), a multi-domain benchmark for hierarchical relation extraction. Our framework establishes a new state of the art on SciERC, SciER, and SPHERE, improving NER by 8.08% and RE by 5.99% on out-of-distribution tests. In zero-shot settings, gains reach 10.76% for NER and 26.2% for RE.
Abstract (translated)
自动化知识图谱（KG）构建对于快速增长的科研文献的探索至关重要。然而，现有方法难以识别长多词实体，通常无法跨领域泛化，且往往忽视科学知识的层次性。虽然通用大语言模型（LLMs）具有适应性，但它们在专业任务上计算成本高昂且准确率不稳定。因此，当前KG普遍浅层且不一致，限制了其用于探索和综合的效用。我们提出一个可扩展的零样本科学KG构建两阶段框架。第一阶段Z-NERD引入了（i）正交语义分解（OSD），通过隔离文本中的语义“转向”来促进领域无关实体识别；（ii）多尺度TCQK注意力机制，通过n-gram感知注意力头捕获连贯的多词实体。第二阶段HGNet通过层次感知消息传递执行关系抽取，显式建模父级、子级和同级关系。为强化全局一致性，我们引入两个互补目标：可微层次损失（抑制循环和捷径边）以及连续抽象场（CAF）损失（在欧氏空间的可学习轴上嵌入抽象层级）。这是首个将层次抽象形式化为标准欧氏嵌入中连续属性的方法，为双曲方法提供了更简单的替代方案。我们发布了SPHERE（此https链接），一个用于层次关系抽取的多领域基准。我们的框架在SciERC、SciER和SPHERE上建立了新的最先进水平，在分布外测试中将NER提升8.08%、RE提升5.99%。在零样本设置中，NER和RE的增益分别达到10.76%和26.2%。
URL
https://arxiv.org/abs/2603.23136
PDF
-
Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
2026-03-23 23:22:58Pouria Mortezaagha, Arya RahgozarAbstract
Retrieval-Augmented Generation (RAG) systems for biomedical literature are typically evaluated using ranking metrics like Mean Reciprocal Rank (MRR), which measure how well the system identifies the single most relevant chunk. We argue that for full-text scientific documents, this paradigm is incomplete: it rewards retrieval precision while ignoring retrieval breadth -- the ability to surface evidence from across a document's structural sections. We propose GraLC-RAG, a framework that unifies late chunking with graph-aware structural intelligence, introducing structure-aware chunk boundary detection, UMLS knowledge graph infusion, and graph-guided hybrid retrieval. We evaluate six strategies on 2,359 IMRaD-filtered PubMed Central articles using 2,033 cross-section questions and two metric families: standard ranking metrics (MRR, Recall@k) and structural coverage metrics (SecCov@k, CS Recall). Our results expose a sharp divergence: content-similarity methods achieve the highest MRR (0.517) but always retrieve from a single section, while structure-aware methods retrieve from up to 15.6x more sections. Generation experiments show that KG-infused retrieval narrows the answer-quality gap to delta-F1 = 0.009 while maintaining 4.6x section diversity. These findings demonstrate that standard metrics systematically undervalue structural retrieval and that closing the multi-section synthesis gap is a key open problem for biomedical RAG.
Abstract (translated)
用于生物医学文献的检索增强生成（RAG）系统通常采用平均倒数排名（MRR）等排序指标进行评估，这类指标衡量系统识别单个最相关文本块的能力。我们认为，对于全文科学文献，这一范式存在不足：它奖励检索精度，却忽视了检索广度——即从文档各结构章节中提取证据的能力。我们提出了GraLC-RAG框架，该框架将延迟分块与图感知结构智能相结合，引入了结构感知分块边界检测、UMLS知识图谱注入以及图引导混合检索。我们在2,359篇经IMRaD筛选的PubMed Central文章上评估了六种策略，使用2,033个跨章节问题以及两类指标：标准排序指标（MRR、Recall@k）和结构覆盖指标（SecCov@k、CS Recall）。我们的结果揭示了显著分化：内容相似性方法达到最高MRR（0.517），但始终仅从单一章节检索；而结构感知方法检索的章节数量高达前者的15.6倍。生成实验表明，知识图谱注入的检索将答案质量差距缩小至delta-F1 = 0.009，同时保持4.6倍的章节多样性。这些发现证明，标准指标系统性地低估了结构检索的价值，而弥合多章节综合的差距是生物医学RAG领域一个关键未决问题。
URL
https://arxiv.org/abs/2603.22633
PDF
