{"ID":2878288,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19428","arxiv_id":"2508.19428","title":"Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)","abstract":"We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines retrieval-augmented prompting, zero-shot classification, and attention-based graph modeling -- each tailored to the demands of the respective task. For Task A, we jointly extract domain-specific terms and their ontological types using a retrieval-augmented generation (RAG) pipeline. Training data was reformulated into a document to terms and types correspondence, while test-time inference leverages semantically similar training examples. This single-pass method requires no model finetuning and improves overall performance through lexical augmentation Task B, which involves assigning types to given terms, is handled via a dual strategy. In the few-shot setting (for domains with labeled training data), we reuse the RAG scheme with few-shot prompting. In the zero-shot setting (for previously unseen domains), we use a zero-shot classifier that combines cosine similarity scores from multiple embedding models using confidence-based weighting. In Task C, we model taxonomy discovery as graph inference. Using embeddings of type labels, we train a lightweight cross-attention layer to predict is-a relations by approximating a soft adjacency matrix. These modular, task-specific solutions enabled us to achieve top-ranking results in the official leaderboard across all three tasks. Taken together these strategies showcase the scalability, adaptability, and robustness of LLM-based architectures for ontology learning across heterogeneous domains. Code is available at: https://github.com/BelyaevaAlex/LLMs4OL-Challenge-Alexbek","short_abstract":"We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines retrieval-augmented prompting, zero-shot classification, and attention-based graph modelin...","url_abs":"https://arxiv.org/abs/2508.19428","url_pdf":"https://arxiv.org/pdf/2508.19428v1","authors":"[\"Aleksandra Beliaeva\",\"Temurbek Rahmatullaev\"]","published":"2025-08-26T20:50:16Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LO\",\"cs.SC\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610472,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2878288,"paper_url":"https://arxiv.org/abs/2508.19428","paper_title":"Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)","repo_url":"https://github.com/BelyaevaAlex/LLMs4OL-Challenge-Alexbek","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}