Search papers, labs, and topics across Lattice.
This paper tackles the challenges of ontology learning from text by employing a retrieval-augmented few-shot prompting pipeline using the Qwen2.5-14B-Instruct model alongside all-MiniLM-L6-v2 for demonstration retrieval. The system achieves high performance metrics, including a Semantic Graph Similarity of 0.8692 and a Term-Typing F1 of 0.9200 on the Ontology Extension Reuse Task, while also addressing the limitations of closed, taxonomy-oriented relation vocabularies. Despite these successes, the inability to extract non-taxonomic relations underscores the need for more flexible approaches in ontology learning.
Achieving a Term-Typing F1 of 0.9200 reveals the potential of retrieval-augmented generation in overcoming traditional ontology learning hurdles.
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.
