REVAL：大视觉语言模型可靠性与价值观的综合评估
REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models
AI总结：
本研究提出综合基准REVAL，含14.4万条VQA样本，从可靠性与价值观两大维度评估26款大视觉语言模型，发现其在对抗场景、隐私保护等方面存在漏洞，为模型优化提供方向。
摘要：
大视觉语言模型（LVLM）的快速发展凸显了构建能从多维度评估这类模型的综合评估框架的必要性。现有基准虽聚焦感知能力、认知能力、对抗攻击安全性等特定方面，但往往缺乏足够的广度与深度，无法全面认识LVLM的优势与局限。为填补这一空白，我们提出REVAL——一个专为评估LVLM的可靠性（Reliability）与价值观（Values）设计的综合基准。REVAL包含超过14.4万条图文视觉问答（VQA）样本，分为两大核心模块：可靠性模块评估真实性（如感知准确率、幻觉倾向）与鲁棒性（如对对抗攻击、排版攻击、图像损坏的抵御能力）；价值观模块评估伦理问题（如偏见、道德理解）、安全问题（如毒性、越狱漏洞）与隐私问题（如隐私意识、隐私泄露）。我们评估了26个模型，包括主流开源LVLM以及GPT-4o、Gemini-1.5-Pro等知名闭源模型。研究结果显示，当前LVLM虽在感知任务、规避毒性内容方面表现出色，但在对抗场景、隐私保护、伦理推理方面存在明显漏洞。这些发现指明了未来改进的关键方向，为开发更安全、可靠、符合伦理的LVLM提供指引。REVAL为研究人员系统评估、对比LVLM提供了稳健框架，将推动该领域的发展。
英文摘要：
The rapid evolution of Large Vision-Language Models (LVLMs) has highlighted the necessity for comprehensive evaluation frameworks that assess these models across diverse dimensions. While existing benchmarks focus on specific aspects such as perceptual abilities, cognitive capabilities, and safety against adversarial attacks, they often lack the breadth and depth required to provide a holistic understanding of LVLMs' strengths and limitations. To address this gap, we introduce REVAL, a comprehensive benchmark designed to evaluate the \textbf{RE}liability and \textbf{VAL}ue of LVLMs. REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability, which assesses truthfulness (\eg, perceptual accuracy and hallucination tendencies) and robustness (\eg, resilience to adversarial attacks, typographic attacks, and image corruption), and Values, which evaluates ethical concerns (\eg, bias and moral understanding), safety issues (\eg, toxicity and jailbreak vulnerabilities), and privacy problems (\eg, privacy awareness and privacy leakage). We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro. Our findings reveal that while current LVLMs excel in perceptual tasks and toxicity avoidance, they exhibit significant vulnerabilities in adversarial scenarios, privacy preservation, and ethical reasoning. These insights underscore critical areas for future improvements, guiding the development of more secure, reliable, and ethically aligned LVLMs. REVAL provides a robust framework for researchers to systematically assess and compare LVLMs, fostering advancements in the field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
