Detecting Contradictory Evidence on Drug-Disease Associations at Scale
Contradictory claims about drug efficacy across randomized controlled trials (RCTs) complicate evidence-based medicine, yet existing automated methods classify isolated sentence pairs and do not explain why studies disagree. We present DrugCon, a large language model (LLM)-based framework that extracts study conclusions from RCT abstracts, links these claims when they concern the same drug-disease association, detects contradictions with counterfactual reasoning, and explains them using a taxonomy of ten study-level factors such as population, dosage, and outcome measures. Applying DrugCon to 224,756 RCT abstracts, we built DrugCon-Bench, an exhaustively annotated benchmark of 542 contradictory claim pairs from 819 abstracts. Most contradictions involve more than one study-level factor (75.5%). The most common are differences in outcome measures (64.0%), populations (51.3%), and dosage or exposure duration (35.6%). DrugCon achieves an F1 score of 0.744 for contradiction detection, outperforming rule-based, supervised, and natural language inference baselines, and an F1 of 0.482 for identifying explanatory study factors. DrugCon enables scalable and explainable analysis of contradictory clinical evidence.
Authors
- Halil Kilicoglu B (ORCID: https://orcid.org/0000-0003-3987-9393)
- Joseph T. Menke (ORCID: https://orcid.org/0000-0002-7374-7549)
- Zhiyong Lu (ORCID: https://orcid.org/0000-0001-9998-916X)
- Mengfei Lan (ORCID: https://orcid.org/0000-0002-0237-0406)
- Shiwei Liu
Institutions
- University of Illinois Urbana-Champaign (US)
- United States National Library of Medicine (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-11-12
- DOI
- https://doi.org/10.64898/2026.11.11.26367856
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- preprint