mlsanityData to 14 Oct 2026

BiasICL: In-Context Learning and Demographic Biases of Vision Language Models

arXiv 2503.02334 ↗First posted 4 Mar 2025cs.CV cs.AIcited by 2

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Vision language models (VLMs) show promise in medical diagnosis, but their performance across demographic subgroups when using in-context learning (ICL) remains poorly understood. We examine how the demographic composition of demonstration examples affects VLM performance in two medical imaging tasks: skin lesion malignancy prediction and pneumothorax detection from chest radiographs. Our analysis reveals that ICL influences model predictions through multiple mechanisms: (1) ICL allows VLMs to learn subgroup-specific disease base rates from prompts and (2) ICL leads VLMs to make predictions that perform differently across demographic groups, even after controlling for subgroup-specific disease base rates. Our empirical results inform best-practices for prompting current VLMs (specifically examining demographic subgroup performance, and matching base rates of labels to target distribution at a bulk level and within subgroups), while also suggesting next steps for improving our theoretical understanding of these models.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 24 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

18 of 24 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks1 Oct
  2. 2024In-context learning enables multimodal large language models to classify cancer pathology images12 Mar
  3. 2024Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging22 Feb

Other references · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  3. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  4. 2023Large Language Modelscited by 780
  5. 2018Confounding variables can degrade generalization performance of radiological deep learning modelscited by 379
  6. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
  7. 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 216
  8. 2024Lessons from the Trenches on Reproducible Evaluation of Language Modelscited by 179
  9. 2021Reading Race: AI Recognises Patient's Racial Identity In Medical Imagescited by 156
  10. 2024LAB-Bench: Measuring Capabilities of Language Models for Biology Researchcited by 156
  11. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  12. 2021Disparities in Dermatology AI: Assessments Using Diverse Clinical Imagescited by 134
3 more
  1. 2024Many-Shot In-Context Learning in Multimodal Foundation Modelscited by 67
  2. 2023How Robust are LLMs to In-Context Majority Label Bias?cited by 14
  3. 2020An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Visual concept ranking uncovers medical shortcuts used by large multimodal modelscited by 0
  2. 2026FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Makingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMs
  2. 2026Medical Context Distorts Decisions in Clinical Vision Language Models
  3. 2026How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective
  4. 2026How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
  5. 2025How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
  6. 2024Knowledge-grounded Adaptation Strategy for Vision-language Models: Building Unique Case-set for Screening Mammograms for Residents Training
  7. 2024MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models
  8. 2025Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification