Event date · · MIOH

Fine-Grained Multi Image Object Hallucination Benchmark

FACT STATEMENT

A benchmark called MIOH is introduced to systematically evaluate object hallucination in multimodal large language models across four tasks (existence, counting, attribute, position) and three multi-image reasoning patterns (comprehensive, comparative, selective) under three adversarial pressures (visual context scale, perceptual difficulty, contextual bias). Evaluation of 29 models reveals that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns.

What happened

MIOH is a fine-grained multi-image object hallucination benchmark that evaluates object hallucination across four foundational tasks and three multi-image reasoning patterns under controlled adversarial pressures. Evaluation of 29 models shows that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns across different reasoning patterns and tasks.

Technical significance

The benchmark decomposes hallucination triggers into visual context scale, perceptual difficulty, and contextual bias, enabling diagnosis of how multi-image reasoning demands interact with visual complexity. Distinct failure patterns across reasoning patterns suggest that hallucination is not solely a perceptual issue but also arises from reasoning and attention mechanisms.

Industry impact

The finding that leading models such as GPT-5 and Gemini-2.5-Pro still exhibit object hallucination in multi-image settings indicates a persistent reliability gap for enterprise and consumer applications requiring cross-image reasoning, such as document analysis, surveillance, and visual question answering.

Decision value

For businesses deploying multimodal AI in multi-image workflows, MIOH provides a diagnostic tool to assess failure modes and select models based on task-specific hallucination rates, potentially reducing errors in high-stakes applications like medical imaging, legal document review, and autonomous systems.

What to watch

Observable next signals include whether model developers release updates targeting multi-image hallucination, whether MIOH is adopted as a standard evaluation in model cards, and whether downstream applications implement mitigation strategies such as retrieval-augmented verification or explicit reasoning constraints.

DECISION BRIEF

Turn the evidence into a decision.

See how AIGC.NEWS separates verified change, judgment, and the next signal to watch.