SOURCE-LINKED INTELLIGENCE

Fine-Grained Multi Image Object Hallucination Benchmark

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundamentally limited by object hallucination-generating plausible yet factually inconsistent descriptions about objects. Existing benchmarks, designed primarily for single-image settings or providing only high-level multi-image assessments, cannot systematically diagnose how visual complexity and reasoning demands trigger hallucination. To address this gap, we introduce MIOH, a fine-grained multi-image object hallucinatio

Read original source ↗ Open in workspace

recordType

paper

region

Global