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

arXiv: https://arxiv.org/abs/2606.11208 · HTML: https://mlsanity.com/paper/2606.11208/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.08067/) (2024)
- [WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia](https://mlsanity.com/paper/2406.13805/) (2024)
- [Evidence Inference 2.0: More Data, Better Models](https://mlsanity.com/paper/2005.04177/) (2020)
- [DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models](https://mlsanity.com/paper/2408.01933/) (2024)
- [Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation](https://mlsanity.com/paper/2411.16638/) (2024)
- [HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2512.02299/) (2025)

## Abstract (arXiv)

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.