Scalable Construction of a Lung Cancer Knowledge Base: Profiling Semantic Reasoning in LLMs

TL;DR

This paper introduces a scalable pipeline for constructing a lung cancer knowledge base using OpenIE and NER, significantly improving biomedical NLP performance for LLM fine-tuning.

Contribution

It presents a novel, scalable method for building a domain-specific biomedical knowledge base leveraging OpenIE and NER, enhancing LLM fine-tuning.

Findings

Improved semantic coherence in LLM outputs.

Enhanced performance on biomedical NLP tasks.

Demonstrated effectiveness of OpenIE-derived datasets.

Abstract

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.