Metraipolis › archive › dc_20aff3901d01
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis — arXiv:2609.40361
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40361
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:14:30.365Z
- SHA-256 of the archived text
aac814ad4fc85ad43c39c0b9ab15983c1675d290853214b1f7db09eb87648fec- Stable URL of this page
https://metraipolis.com/documento/dc_20aff3901d01
How to cite
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis — arXiv:2609.40361 — arXiv (en), https://arxiv.org/abs/2609.40361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20aff3901d01 (Metraipolis archive dc_20aff3901d01, sha256 aac814ad4fc85ad43c39c0b9ab15983c1675d290853214b1f7db09eb87648fec)
BibTeX
@misc{dc20aff3901d01,
title = {Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis — arXiv:2609.40361},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40361},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20aff3901d01; sha256 aac814ad4fc85ad43c39c0b9ab15983c1675d290853214b1f7db09eb87648fec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptation pipelines remain anchored to accuracy-based objectives. Clinical data are heavily class-imbalanced: a constant-majority predictor can score above 90% accuracy while being clinically useless. We therefore evaluate and optimize for AUROC, a threshold-free score that ranks positives above negatives and is invariant to class balance. We focus on prompt optimization in MLLMs. Reflective methods such as GEPA use a binary scores matrix with one row per evaluation instance and one column per candidate prompt; cells record per-instance correctness, so the column average is accuracy and drives candidate selection. We introduce pair-level Pareto prompt evolution (Ranking-PE), which replaces each correctness row with a pairwise-ordering row over (positive, negative) instance pairs: the cell is 1 if the candidate scores the positive higher than the paired negative. The column average then equals empirical AUROC (by the Wilcoxon-Mann-Whitney identity). We apply this swap at all three layers the prompt evolution search reads from - the scores matrix that decides Pareto dominance, the per-example feedback to the reflection LM, and final candidate selection - at no extra model calls and with no surrogate loss. Across three diseases on MIMIC, accuracy-based prompt evolution can degrade ranking; Ranking-PE reverses this, beating the accuracy-based recipe by +5.8 AUROC pp on fine-tuned Qwen3-VL-8B and +16.2 pp on MedGemma-4B. Ablations examine each design component and show that a medical-grade visual backbone - via vision-encoder-tuned SFT or medical pretraining - is a prerequisite that prompt search cannot replace - our recipe extends reflective prompt evolution from text-only data to multimodal clinical decision-making. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.40361 — 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 2026-10-07T12:44:51.994Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).