How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading). We introduce SciFigBench, a diagnostic VLM benchmark for scientific figure understanding that jointly evaluates perception, reasoning, and behavioral reliability under uncertainty. It contains 250 figures wi
Record details
Published: 13 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Healthcare
Retrieved: 14 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.
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
arXiv cs.AI · 13 August 2026
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
arXiv · 13 August 2026
CAPRI: Contract-Aware Proof Repair for Isabelle
arXiv cs.AI · 13 August 2026
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
arXiv cs.AI · 13 August 2026
Tracing Methamphetamine abuse in under-treatment drivers: How biomechanical and oculomotor features help detect at-risk drivers?
arXiv cs.HC · 13 August 2026
Exploring Perceptions of Leveraging AI to Improve Outcomes in Maternal, Sexual, and Reproductive Health in Sub-Saharan Africa: Exploratory Qualitative Study
JMIR (Journal of Medical Internet Research) · 13 August 2026
How to cite this record
ethics.ai (13 August 2026), “How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures,” evidence record 19448, https://ethics.ai/record/19448 (originally published by arXiv cs.AI).
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.