Metraipolis › archive › dc_7be40329bbe2

Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models — arXiv:2609.32185

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32185
License (as archived): CC0-1.0
Archived: 2026-10-07T22:39:35.250Z
SHA-256 of the archived text: d219773116541434a9b7bb583de34f4a71b7b9d86c0da6413f4bdb42e3849be8
Stable URL of this page: https://metraipolis.com/documento/dc_7be40329bbe2

How to cite

Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models — arXiv:2609.32185 — arXiv (en), https://arxiv.org/abs/2609.32185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7be40329bbe2 (Metraipolis archive dc_7be40329bbe2, sha256 d219773116541434a9b7bb583de34f4a71b7b9d86c0da6413f4bdb42e3849be8)

BibTeX

@misc{dc7be40329bbe2,
  title = {Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models — arXiv:2609.32185},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32185},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7be40329bbe2; sha256 d219773116541434a9b7bb583de34f4a71b7b9d86c0da6413f4bdb42e3849be8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pathology vision-language models (VLMs) are conventionally evaluated by accuracy, but accuracy alone does not measure evidence use: it may conflate dataset contamination, prior knowledge, and image evidence. In a motivating study of lymph-node metastasis prediction, we found that most public pathology VLMs showed minimal differences when changing from feeding the models with whole-slide images, an annotated lesion, or no image at all. To better understand the specific features leveraged by these models, this paper presents two contributions aimed at disentangling these factors. First, we present CleanSlide, a TCGA-based VQA benchmark designed to eliminate image- and question-side contamination. It contains 149K audited multiple-choice questions over 9,985 slides, with patient- and tissue-source-disjoint splits. Every question is audited for option shortcuts, stem leakage, cross-split duplication, and blind solvability. Second, we propose Pair-DPO, a preference loss over counterfactual slide pairs from the same question and source. By controlling for shared confounding factors, Pair-DPO cancels out the question-attributable signal and leaves image evidence as the source of preference. Specifically, each pair consists of two real slides with opposite, verified findings, introducing neither editing artifacts nor unverified labels for diffuse or graded features such as invasion, necrosis, and tumor grade. Experiments show that our method gains 15.29% from image evidence on the CleanSlide, compared with 2.81% for the best published model. On the external CPTAC and BCNB cohorts, our method achieves accuracies of 57.6% and 59.0%, outperforming all other evaluated models by 9.7% and 3.4%, respectively. We will release the benchmark and code.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32185 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:28.580Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).