Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge. We explore these failures separately using two diagnostic paradigms: (1) probing whether visual information is available, via image reconstruction, and (2) measuring multimodal context sensitivity, the extent to which the model foll
Record details
Published: 27 July 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Healthcare
Retrieved: 5 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Traditional, Complementary, and Integrative Medicine on X (Formerly Twitter) From 2015 to 2024 Across English, Spanish, and French: Retrospective Observational Study
JMIR (Journal of Medical Internet Research) · 27 July 2026
Mapping Machine Learning–Driven Cybersecurity Solutions in Health Care: Scoping Literature Review
JMIR (Journal of Medical Internet Research) · 27 July 2026
Shape-Based Inductive Bias for Glioma Grading from Tumor Contours
arXiv cs.LG · 27 July 2026
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
arXiv cs.AI · 27 July 2026
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
arXiv cs.AI · 27 July 2026
All living things emit a faint glow. Could this light be useful?
Nature Machine Intelligence · 27 July 2026
How to cite this record
ethics.ai (27 July 2026), “Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models,” evidence record 16232, https://ethics.ai/record/16232 (originally published by HuggingFace Daily Papers).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.