Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• Current vision-language model benchmarks are poorly suited to detect commonsense-driven hallucination because they use commonsense-consistent imagery where visual evidence and priors typically agree.limitation 90%
• CDH-Bench is a benchmark designed to create explicit visual evidence-commonsense conflicts across three dimensions: counting anomalies, relational anomalies, and attribute anomalies.method 95%
• Even strong vision-language models remain vulnerable to prior-driven normalization under visual evidence-commonsense conflict.result 85%
• The Commonsense Collapse Rate (CCR) metric provides a sharper diagnostic signal than accuracy alone by quantifying how often models revert to commonsense alternatives when they fail.method 80%
• CDH-Bench contains 600 images organized as 300 counterfactual-commonsense image pairs, yielding 1,200 evaluated instances across different conditions and formats.method 90%
• Counterfactual Accuracy (CF-Acc) is the primary measure of visual fidelity under visual evidence-commonsense conflict.method 85%
• Commonsense-driven hallucination matters most in domains like medical imaging, quality inspection, scientific discovery, and forensics where anomalies are critical.market 80%
• The Relative Prior Dependency (RPD) metric measures how much capability is lost when visual evidence conflicts with commonsense, normalized by baseline performance.method 75%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card