Scalable Construction of a Lung Cancer Knowledge Base: Profiling Semantic Reasoning in LLMs
This addresses the need for scalable, low-cost methods to build domain-specific knowledge bases for fine-tuning LLMs in oncology, where precision is critical, though it is incremental as it applies existing OpenIE and NER techniques to new biomedical data.
This study tackled the problem of constructing a structured knowledge base for lung cancer to improve LLM performance in biomedical research, resulting in significantly enhanced semantic coherence and performance metrics like ROUGE and BERTScore for fine-tuned T5 models.
The integration of Large Language Models (LLMs) into biomedical research offers new opportunities for domainspecific reasoning and knowledge representation. However, their performance depends heavily on the semantic quality of training data. In oncology, where precision and interpretability are vital, scalable methods for constructing structured knowledge bases are essential for effective fine-tuning. This study presents a pipeline for developing a lung cancer knowledge base using Open Information Extraction (OpenIE). The process includes: (1) identifying medical concepts with the MeSH thesaurus; (2) filtering open-access PubMed literature with permissive licenses (CC0); (3) extracting (subject, relation, object) triplets using OpenIE method; and (4) enriching triplet sets with Named Entity Recognition (NER) to ensure biomedical relevance. The resulting triplet sets provide a domain-specific, large-scale, and noise-aware resource for fine-tuning LLMs. We evaluated T5 models finetuned on this dataset through Supervised Semantic Fine-Tuning. Comparative assessments with ROUGE and BERTScore show significantly improved performance and semantic coherence, demonstrating the potential of OpenIE-derived resources as scalable, low-cost solutions for enhancing biomedical NLP.