pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning

• URL: http://arxiv.org/abs/2608.27101v2
• Date: Tue, 01 Sep 2026 12:50:31 GMT
• Title: pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning
• Abstract summary: Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs)<n>In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Reuse Extension Task (Task B)<n>Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B.<n>For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's
• Score: 5.0147105079462415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produce inconsistent formats, and favor hierarchical over associative relations. In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Extension Reuse Task (Task B) using an offline retrieval-augmented few-shot prompting pipeline. Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B. A left-truncated context-windowing strategy preserves task instructions within long prompts. For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's closed term/type vocabulary and removing duplicates of the initial ontology. The approach achieves Semantic Graph Similarity of 0.8692, Term-Typing F1 of 0.9200, and Taxonomy Discovery F1 of 0.8540 on Task B, while Task A achieves 0.7416 Semantic Graph Similarity. However, no non-taxonomic relations are extracted, highlighting limitations of closed, taxonomy-oriented relation vocabularies.

Related papers

• GrOIL: Graph-Grounded Domain Ontology Induction with Constrained LLM Mediation [1.029029220360574]
  We present a seven-stage graph-grounded pipeline that converts domain documents into a complete Web Ontology Language (OWL) Terminological Box (TBox) without any unconstrained generation step.<n>Ontology growth analysis provides evidence consistent with vocabulary saturation at scale, demonstrating that the pipeline produces stable, reusable domain representations from large document corpora.
  arXiv  Detail & Related papers  (2026-08-22T23:15:47Z)
• TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning [35.18087118865049]
  TAROT is a GNN-based framework that encodes the structural and semantic prior by constructing and refining a task-adaptive semantic graph from this prior.<n>To mitigate structural noise introduced by the hallucination of LLMs, TAROT introduces Task-adaptive Semantic Graph Refinement.
  arXiv  Detail & Related papers  (2026-06-10T04:02:57Z)
• ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation [0.9936176521793759]
  Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions.<n>Current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing.<n>We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction.
  arXiv  Detail & Related papers  (2026-05-19T12:08:19Z)
• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies) [46.54026795022501]
  We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge.<n>Our approach combines retrieval-augmented prompting, zero-shot classification, and attention-based graph modeling.<n>These modular, task-specific solutions enabled us to achieve top-ranking results in the official leaderboard.
  arXiv  Detail & Related papers  (2025-08-26T20:50:16Z)
• LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models [87.68057302738457]
  Text-Attributed Graphs (TAGs) are ubiquitous in real-world scenarios.<n>Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures.<n>We propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning.
  arXiv  Detail & Related papers  (2025-03-05T09:45:22Z)
• DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition [94.90258603217008]
  The MultiCoNER RNum2 shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios. Previous top systems in the MultiCoNER RNum1 either incorporate the knowledge bases or gazetteers. We propose a unified retrieval-augmented system (U-RaNER) for fine-grained multilingual NER.
  arXiv  Detail & Related papers  (2023-05-05T16:59:26Z)
• UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense [0.6404122934568858]
  We describe our adversarial multi-task network, AMTL-Humor, used to detect and rate humor and offensive texts. Our best model consists of an ensemble of all tested configurations, and achieves a 95.66% F1-score and 94.70% accuracy for Task 1a.
  arXiv  Detail & Related papers  (2021-04-13T09:59:05Z)
• Exploring the Hierarchy in Relation Labels for Scene Graph Generation [75.88758055269948]
  The proposed method can improve several state-of-the-art baselines by a large margin (up to $33%$ relative gain) in terms of Recall@50. Experiments show that the proposed simple yet effective method can improve several state-of-the-art baselines by a large margin.
  arXiv  Detail & Related papers  (2020-09-12T17:36:53Z)
• Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions [87.33156149634392]
  We critically examine RefCOg, a standard benchmark for visual referring expression recognition. We show that 83.7% of test instances do not require reasoning on linguistic structure. We propose two methods, one based on contrastive learning and the other based on multi-task learning, to increase the robustness of ViLBERT.
  arXiv  Detail & Related papers  (2020-05-04T17:09:15Z)

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.