SEMA at LLMs4OL 2025 Task C: Prompt-Decoupled Fine-Tuning on MatOnto with LLaMA

Abstract

This paper presents our submission to Task C (Relation Extraction) of the LLMs4OL 2025 Challenge, which investigates the ability of Large Language Models (LLMs) to identify semantic and taxonomic relations between ontology types. Focusing on the MatOnto subtask—selected for its manageable size—we explore the performance of open-source models under resource constraints. We fine-tune LLaMA 3.1–8B using LoRA adapters and evaluate various strategies including contrastive negative sampling, prompt inversion, and system prompt variation. Inspired by recent findings on prompt sensitivity, we adopt a cross-template setup where the model is trained with one prompt format and tested with another semantically equivalent variant. Our experiments suggest that prompt-decoupling can improve generalization and mitigate overfitting to specific phrasings. While our results are modest, they offer insights into the challenges of adapting LLMs to structured relation extraction tasks and highlight practical considerations for tuning under constrained resources.