Fine-Grained Multi Image Object Hallucination Benchmark

2026-08-31

AI Summary

本文针对多图像场景下模型产生对象幻觉的问题，通过构建MIOH基准，系统评估不同任务和推理模式下的幻觉情况，揭示了幻觉产生的原因。

Abstract

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 hallucination benchmark that systematically evaluates object hallucination across four foundational tasks (existence, counting, attribute, position) through three multi-image reasoning patterns (comprehensive, comparative, selective) under three controlled adversarial pressures (visual context scale, perceptual difficulty, contextual bias). Through evaluation of 29 models, we reveal 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. Our evaluation reveals that hallucination stems not merely from perceptual failures but from integration-stage limitations when maintaining object representations across multiple images. MIOH provides a controlled framework for analyzing multi-image object hallucination and serves as a critical evaluation tool for developing more reliable multimodal AI systems.

Problem

• Multimodal Large Language Models
• object hallucination
• multi-image scenarios
• visual complexity
• reasoning demands

Innovation

• multi-image object hallucination
• controlled adversarial pressures
• reasoning patterns
• integration-stage limitations