Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction

arXiv:2404.09593v1 Announce Type: new
Abstract: Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning when given appropriate instructions. However, they often miss out when extracting from complex sentences. In this paper, we design an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks. The framework includes an evaluation model …

abstract acquisition arxiv collaboration cs.cl extract extraction few-shot few-shot learning fine-tuning however improving knowledge knowledge acquisition language language models large language large language models recall relational role set simple through type vital