Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field
Knowledge Organization Systems like Ontologies and taxonomies are fundamental for structuring scientific knowledge, yet their manual curation presents a persistent bottleneck in knowledge management. While Large Language Models (LLMs) offer a scalable mechanism for automated ontology generation, their capacity to classify complex, domain-specific semantics requires systematic evaluation. In this paper, we assess the performance of five small, open-source LLMs (up to 9 billion parameters) in identifying semantic relationships between biomedical concepts. To support this evaluation, we introduce
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%AI for Scientific Literature Mining: PubMed, Semantic Scholar, and What Actually Works - Technology Networks →
- PossiblePossibly related (embedding) · 46%Empowering biomedical evidence exploration and synthesis with deep knowledge graph research →
- FuzzySimilar title/name (fuzzy) · 59%halfrost/Halfrost-Field →
“Fuzzy title match (0.73): “Benchmarking Resource-Efficient LLMs for Research Topic Onto” ≈ “halfrost/Halfrost-Field””
- FuzzySimilar title/name (fuzzy) · 59%google-research/google-research →
“Fuzzy title match (0.73): “Benchmarking Resource-Efficient LLMs for Research Topic Onto” ≈ “google-research/google-research””
- LinkedLinked via arxiv author · 85%Tanay Aggarwal →
“Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field”
- LinkedLinked via arxiv author · 85%Angelo Salatino →
“Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field”
- LinkedLinked via arxiv author · 85%Francesco Osborne →
“Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field”
- LinkedLinked via arxiv author · 85%Enrico Motta →
“Benchmarking Resource-Efficient LLMs for Research Topic Ontology Generation in the Biomedical Field”