# SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning

arXiv: https://arxiv.org/abs/2506.21355 · HTML: https://mlsanity.com/paper/2506.21355/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2305.17100/) (2023)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [Almanac: Retrieval-Augmented Language Models for Clinical Medicine](https://mlsanity.com/paper/2303.01229/) (2023)
- [What Makes Multimodal In-Context Learning Work?](https://mlsanity.com/paper/2404.15736/) (2024)
- [VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning](https://mlsanity.com/paper/2403.13164/) (2024)
- [Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?](https://mlsanity.com/paper/2311.18021/) (2023)
- [Style-Aware Radiology Report Generation with RadGraph and Few-Shot Prompting](https://mlsanity.com/paper/2310.17811/) (2023)

## Built on by (most cited first, 5 of 5)

- [Stability of In-Context Learning: A Spectral Coverage Perspective](https://mlsanity.com/paper/2509.20677/) (2025)
- [MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation](https://mlsanity.com/paper/2511.13135/) (2025)
- [DiscoVerse: Multi-Agent Pharmaceutical Co-Scientist for Traceable Drug Discovery and Reverse Translation](https://mlsanity.com/paper/2511.18259/) (2025)
- [Algorithmic Authority and the Clinical Standard of Care](https://mlsanity.com/paper/2606.00044/) (2026)
- [MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models](https://mlsanity.com/paper/2609.39920/) (2026)

## Abstract (arXiv)

Multimodal in-context learning (ICL) remains underexplored despite significant potential for domains such as medicine. Clinicians routinely encounter diverse, specialized tasks requiring adaptation from limited examples, such as drawing insights from a few relevant prior cases or considering a constrained set of differential diagnoses. While multimodal large language models (MLLMs) have shown advances in medical visual question answering (VQA), their ability to learn multimodal tasks from context is largely unknown. We introduce SMMILE, the first expert-driven multimodal ICL benchmark for medical tasks. Eleven medical experts curated problems, each including a multimodal query and multimodal in-context examples as task demonstrations. SMMILE encompasses 111 problems (517 question-image-answer triplets) covering 6 medical specialties and 13 imaging modalities. We further introduce SMMILE++, an augmented variant with 1038 permuted problems. A comprehensive evaluation of 15 MLLMs demonstrates that most models exhibit moderate to poor multimodal ICL ability in medical tasks. In open-ended evaluations, ICL contributes only an 8% average improvement over zero-shot on SMMILE and 9.4% on SMMILE++. We observe a susceptibility for irrelevant in-context examples: even a single noisy or irrelevant example can degrade performance by up to 9.5%. Moreover, we observe that MLLMs are affected by a recency bias, where placing the most relevant example last can lead to substantial performance improvements of up to 71%. Our findings highlight critical limitations and biases in current MLLMs when learning multimodal medical tasks from context. SMMILE is available at https://smmile-benchmark.github.io.