The paper presents a lightweight, scalable workflow for refining ontologies, demonstrated on the CASTON casting-domain ontology. It combines a fine‑tuned ontology embedding model to generate candidate axioms and replacement options with a Large Language Model (LLM) that proposes repair suggestions. In a small expert evaluation, the default setup—using a CASTON‑fine‑tuned embedding model and Qwen3‑8B—yielded high‑confidence repairs that were all accepted by domain experts.
arXiv:2609.08174v1 Announce Type: new Abstract: We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs a...
arXiv:2610.18672v1 Announce Type: cross Abstract: Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among m...
The paper presents an automated framework for building ontology networks by discovering typed semantic links between concepts across domains. It uses domain‑adapted DistilBERT embeddings, clustering to prune candidates, and GPT‑4o for generating interpretable relationships, reducing 800k raw pairs to 95k high‑quality candidates. Human validation on 429 links shows an 80.19% precision and 0.890 F1, outperforming five similarity‑based baselines and demonstrating the need for LLM reasoning in ontology link construction.
arXiv:2607. 18927v1 Announce Type: new Abstract: We present OntoBook, a method that converts medical ontology structure into pretraining signal for encoder language models.
arXiv:2609.10055v1 Announce Type: cross Abstract: Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical dat...
Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical va...
arXiv:2602.17826v2 Announce Type: replace Abstract: Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in...
arXiv:2506. 01232v2 Announce Type: replace-cross Abstract: Deriving OWL ontologies from relational database schemas supports semantic interoperability and downstream tasks such as knowledge graph population, ontology-based data access, graph-based learning, and automated reasoning.
The paper proposes a behavior-based fusion model that combines large language models (LLMs) with ontology rankers to improve rare-disease diagnosis. By examining ranked lists, agreement, and ontology support, the model learns how much to rely on each system per case, achieving significant recall gains on Phenopacket Store and RAMEDIS benchmarks. Importantly, the fused diagnoses retain candidate-level ontology evidence for inspection.
arXiv:2608.10725v2 Announce Type: replace Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing mo...
The paper introduces Hyperbolic Clinical Ontology Embeddings (HCOE), a method that transforms frozen BioBERT embeddings into a Poincaré ball to capture medical code hierarchies. HCOE employs ontology-guided contrastive learning and coarse‑to‑fine ontology‑path aggregation, leveraging ICD, CCS, and ATC hierarchies. Experiments on MIMIC‑IV demonstrate superior performance in clinical relation prediction, hierarchy transfer, and various predictive tasks such as mortality, readmission, medication recommendation, and rare drug prediction.
The paper introduces UdonCare, a hierarchy‑pruning method that iteratively partitions patients into latent domains using medical ontologies, aiming to improve domain generalization in clinical prediction tasks. It addresses challenges of missing domain labels and lack of clinical insight by discovering hierarchy‑grounded patient domains. Experiments on MIMIC‑III, MIMIC‑IV, and eICU datasets show UdonCare outperforms eight baseline methods across four prediction tasks with significant domain gaps.