KnowHal：用于全面多模态幻觉评估的知识驱动基准
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation
AI总结：
研究针对多模态大语言模型（MLLMs）的幻觉评估缺口，提出知识驱动的KnowHal基准，涵盖四个幻觉维度，经评估发现知识维度是模型最大挑战，多数模型对错误前提鲁棒性有限。
AI中文摘要：
幻觉是开发可信多模态大语言模型（MLLMs）的关键挑战。现有基准主要关注实体、属性和关系幻觉，而知识相关的失败常被单独研究，缺乏覆盖不同幻觉维度的统一评估框架。为解决该问题，我们提出KnowHal，这一基准将知识幻觉明确纳入多模态幻觉评估，涵盖实体、属性、关系、知识四个维度。KnowHal针对共享图像和实体构建成对的正负问题，实现感知错误、知识相关错误和错误前提接受情况的受控比较。该基准包含10个领域、50个类别的1800个样本，通过结合LLM辅助、基于CLIP的过滤和人工验证的半自动化流程构建。我们在KnowHal上评估了14个代表性MLLMs并开展大量分析，结果显示，知识维度对几乎所有被评估模型始终构成最大挑战，且多数模型在负问题上表现大幅下降，表明其对错误前提的鲁棒性有限。通过统一四个幻觉维度并采用成对问题设计，KnowHal填补了现有评估框架的重要空白，可实现对MLLMs幻觉的更全面评估。
英文摘要：
Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus on entity, attribute, and relation hallucinations, knowledge-related failures are often investigated separately, lacking a unified evaluation framework across different hallucination dimensions. To overcome this, we propose \textbf{KnowHal}, a benchmark that explicitly incorporates knowledge hallucination into multimodal hallucination evaluation spanning four dimensions: entity, attribute, relation, and knowledge. KnowHal constructs paired positive and negative questions over shared images and entities, enabling controlled comparisons among perceptual errors, knowledge-related errors, and false-premise acceptance. The benchmark contains 1,800 samples across 10 domains and 50 categories, constructed through a semi-automated pipeline combining LLM assistance, CLIP-based filtering, and human verification. We evaluate 14 representative MLLMs on KnowHal and conduct extensive analyses. Results show that the knowledge dimension consistently presents the greatest challenge for nearly all evaluated models, while most models exhibit substantial performance degradation on negative questions, revealing limited robustness to false premises. By unifying four hallucination dimensions with paired question design, KnowHal addresses an important gap in existing evaluation frameworks and enables a more comprehensive assessment of hallucinations in MLLMs.
