CEDI: A Dynamic, Multi-turn Evaluation Framework Reveals More Realistic Hallucinations in Vision-Language Models

Jul 17, 2026

Researchers introduce CEDI, a framework that evaluates vision-language models (MLLMs) through dynamic, multi-turn interactions rather than static benchmarks. When applied to visual hallucinations, CEDI uncovers significantly more hallucinations that better reflect real-world usage, including those that accumulate over long contexts and those triggered by premise rejection. The framework uses a three-party interaction and diverse probing strategies to elicit more ecologically valid evidence of model performance.

Why it matters: CEDI offers a more realistic and systematic method for assessing the reliability of vision-language models, addressing the limitations of static benchmarks.

Full story at: arXiv AI/ML ↗