Metraipolis › archive › dc_930a980e8ecd
Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity — arXiv:2609.32876
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32876
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:00:43.705Z
- SHA-256 of the archived text
e11deb2e05f2a240cd739696126918715d79e6c1b568b8c8c7b4d703e4d83031- Stable URL of this page
https://metraipolis.com/documento/dc_930a980e8ecd
How to cite
Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity — arXiv:2609.32876 — arXiv (en), https://arxiv.org/abs/2609.32876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_930a980e8ecd (Metraipolis archive dc_930a980e8ecd, sha256 e11deb2e05f2a240cd739696126918715d79e6c1b568b8c8c7b4d703e4d83031)
BibTeX
@misc{dc930a980e8ecd,
title = {Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity — arXiv:2609.32876},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32876},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_930a980e8ecd; sha256 e11deb2e05f2a240cd739696126918715d79e6c1b568b8c8c7b4d703e4d83031},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
State-of-the-art pathology foundation models, trained on millions of histology tiles, can fail to preserve tissue similarity when comparisons cross slide or institution boundaries. We show that general-purpose multimodal LLMs, without being trained as pathology foundation models, consistently outperform these specialized models in cross-domain histological similarity judgments. Using a relative similarity framework that we release as the MOSAIC (Model Similarity Assessment across Institutions and Cohorts) benchmark, we evaluate 17 models across 6 datasets and find that pathology encoders often rank same-institution, different-disease tiles as more similar than same-disease, different-institution tiles, a clinically dangerous failure mode invisible to standard within-domain evaluations. LLMs appear less susceptible to this failure, likely because they perform semantic visual comparison of morphology and tissue architecture rather than relying on shortcut features tied to acquisition context. Scaling training data does not resolve the problem for pathology encoders, implicating the learning objective rather than data coverage. Our results expose a fundamental robustness gap in current pathology foundation models and establish multimodal LLMs as a viable alternative for cross-institutional retrieval, dataset harmonization, and multi-site quality control. Code and data will be released upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.32876 — 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 2026-10-07T20:29:02.486Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).