CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph

• URL: http://arxiv.org/abs/2606.30175v1
• Date: Mon, 29 Jun 2026 11:51:00 GMT
• Title: CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph
• Abstract summary: Existing corpus construction pipelines confine the resulting corpora to flat, undifferentiated document collections.<n>We present Cortex, to our knowledge the first framework that elevates web-scale corpus construction from flat document filtering to structured knowledge organization.
• Score: 54.98647797362972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasingly tailored data requirements, systematic organization of high-quality corpora becomes indispensable. Existing corpus construction pipelines confine the resulting corpora to flat, undifferentiated document collections, universally lacking systematic knowledge organization. We present Cortex, to our knowledge the first framework that elevates web-scale corpus construction from flat document filtering to structured knowledge organization through an Ontological Corpus Graph (OCG), a three-layer heterogeneous structure unifying a quality-refined content layer, a hierarchical lightweight ontology layer via LLM-driven automated evolution, and a cross-domain alignment layer enabling inter-domain association at arbitrary taxonomic resolution. Comprehensive experiments confirm the effectiveness of Cortex. In particular, we leverage the OCG to synthesize CortexBench, a cross-domain search-and-reasoning benchmark whose evaluation across eight frontier LLMs validates the effectiveness of quality refinement, domain organization, and cross-domain data synthesis. We will publicly release the complete codebase, a 24.14B-token refined corpus with its OCG, and CortexBench.

Related papers

• TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale [0.992650024444822]
  TaxCE is a fully automated framework for organizing unstructured feedback text into hierarchical taxonomy.<n>We introduce three corpus-grounded evaluation metrics, Exclusivity, Exhaustivity, and Granularity (EEG), and integrate them into a metrics-in-the-loop iterative refinement mechanism.
  arXiv  Detail & Related papers  (2026-08-31T11:25:25Z)
• Online Continual Learning with Dynamic Label Hierarchies [72.33335166136045]
  We introduce a new problem setting, DHOCL, where severity evolve across granularities and each sample provides supervision at a single hierarchical level.<n>In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency.<n>We propose HALO, which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves.
  arXiv  Detail & Related papers  (2026-05-12T08:20:23Z)
• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
  arXiv  Detail & Related papers  (2026-03-21T14:15:34Z)
• LLM-Driven Ontology Construction for Enterprise Knowledge Graphs [0.0]
  This paper introduces OntoEKG, a pipeline designed to accelerate the generation of domain-specific unstructured from enterprise data.<n>Our approach decomposes the modelling task into two distinct phases: an extraction module that identifies core classes and properties, and an entailment module that logically these elements into a hierarchy before serialising them into standard RDF.<n>Addressing the significant lack of comprehensive benchmarks for end-to-end construction, we adopt a new evaluation dataset derived from documents across the Data, Finance, and Logistics sectors.
  arXiv  Detail & Related papers  (2026-02-01T15:13:30Z)
• Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models [17.169112112753513]
  Large Language Models (LLMs) have achieved remarkable success but remain data-inefficient.<n>Existing synthetic data generation methods for continue pre-training focus on intra-document content.<n>We propose Synthetic-on-Graph (SoG), a synthetic data generation framework that incorporates cross-document knowledge associations.
  arXiv  Detail & Related papers  (2025-05-02T03:40:39Z)
• GyralNet Subnetwork Partitioning via Differentiable Spectral Modularity Optimization [30.044545011553172]
  We propose a differentiable subnetwork framework to modularize the organization of 3HGs within GyralNet.<n>By incorporating topological structural similarity and DTI-derived connectivity patterns as attribute features, our approach provides a biologically meaningful representation of cortical organization.
  arXiv  Detail & Related papers  (2025-03-25T16:33:12Z)
• SFC-GAN: A Generative Adversarial Network for Brain Functional and Structural Connectome Translation [11.070185680800071]
  Structural-Functional Connectivity GAN (SFC-GAN) is a novel framework for bidirectional translation between brain connectomes.<n>To preserve the topological integrity of these connectomes, we employ a structure-preserving loss that guides the model in capturing both global and local connectome patterns.<n>Our framework demonstrates superior performance in translating between SC and FC, outperforming baseline models in similarity and graph property evaluations.
  arXiv  Detail & Related papers  (2025-01-13T04:30:41Z)
• Efficient Multi-View Graph Clustering with Local and Global Structure Preservation [59.49018175496533]
  We propose a novel anchor-based multi-view graph clustering framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG) Specifically, EMVGC-LG jointly optimize anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number.
  arXiv  Detail & Related papers  (2023-08-31T12:12:30Z)
• BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Images [83.82141604007899]
  BCS-Net is a novel network for automatic COVID-19 lung infection segmentation from CT images. BCS-Net follows an encoder-decoder architecture, and more designs focus on the decoder stage. In each BCSR block, the attention-guided global context (AGGC) module is designed to learn the most valuable encoder features for decoder.
  arXiv  Detail & Related papers  (2022-07-17T08:54:07Z)
• Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization [71.79436685992128]
  We propose a two-stage approach, termed structure-preserving activation (SPA), towards fully leveraging the structure information incorporated in convolutional features for WSOL. In the first stage, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network. In the second stage, we propose a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps.
  arXiv  Detail & Related papers  (2021-03-08T03:04:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.