BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts

Abstract:Biomedical findings often seem to conflict across studies, but many of these differences are context-dependent rather than true contradictions. Variations in cohort, geography, assay protocol, disease subtype, and clinical setting can make both claims locally valid. Existing NLI and scientific claim-verification benchmarks reduce such cases to entailment, contradiction, or neutral, failing to capture the contextual structure behind divergence. To address this, we introduce BioDivergence, an evaluation framework with a six-class conflict taxonomy, a 13-axis divergence ontology, and four structured outputs per claim pair: conflict type, divergence axes, dominant confounder, and reconciliation explanation. We release BioDivergence-Silver-v1.0, an article-disjoint silver benchmark of 11,865 claim pairs across five biomedical domains, alongside a legacy deduplicated variant for comparison. Results show notable ranking differences between the two variants, with the fine-tuned reference model dropping about 12 points under the article-disjoint setting, while Mistral-7B-Instruct-v0.3 achieves 0.5523 accuracy and 0.3894 contextual-F1 on the 842-example primary test set. BioDivergence offers a more faithful way to distinguish contextual divergence from direct contradiction and to separate article-level memorization from genuine task learning.

The authors have decided to withdraw this manuscript because substantial revisions to the study design, analysis, and presentation are needed before the work is suitable for public dissemination. A revised version may be submitted separately after these issues have been fully addressed

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2606.11208 [cs.CL]

(or arXiv:2606.11208v2 [cs.CL] for this version)