多模态语言模型对干扰因素的鲁棒性研究
On the robustness of multimodal language model towards distractions
AI总结：
本文基于ScienceQA构建同时引入视觉与文本干扰的科学问答基准，评估VLM鲁棒性，发现GPT-4等模型明显受损，而InternVL2更稳健，且文本干扰影响更大。
摘要：
尽管视觉-语言模型（VLM）在视觉问答等多种应用中取得了显著成功，但其对提示变化的韧性仍是一个探索不足的领域。理解干扰如何影响VLM，对于提升其在现实世界中的适用性至关重要，因为在许多实际场景中，输入可能包含噪声和无关信息。本文旨在在科学问答情境下评估VLM对视觉和文本两类干扰的鲁棒性。我们基于ScienceQA数据集构建了一个新基准，在视觉和文本上下文中同时引入干扰，以评估VLM在这些干扰下的推理能力。研究结果表明，包括GPT-4在内的多数最先进VLM都容易受到各类干扰影响，在面对干扰时推理能力出现明显下降。值得注意的是，InternVL2等模型对这些干扰表现出更高的鲁棒性。我们还发现，模型对文本干扰的敏感性高于视觉干扰。此外，我们探索了提示工程等多种缓解策略，以抵消干扰的影响。尽管这些策略提高了解答准确率，但分析表明仍存在显著的改进空间。
英文摘要：
Although vision-language models (VLMs) have achieved significant success in various applications such as visual question answering, their resilience to prompt variations remains an under-explored area. Understanding how distractions affect VLMs is crucial for improving their real-world applicability, as inputs could have noisy and irrelevant information in many practical scenarios. This paper aims to assess the robustness of VLMs against both visual and textual distractions in the context of science question answering. Built on the ScienceQA dataset, we developed a new benchmark that introduces distractions in both the visual and textual contexts to evaluate the reasoning capacity of VLMs amid these distractions. Our findings reveal that most-of-the-art VLMs, including GPT-4, are vulnerable to various types of distractions, experiencing noticeable degradation in reasoning capabilities when confronted with distractions. Notably, models such as InternVL2 demonstrate a higher degree of robustness to these distractions. We also found that models exhibit greater sensitivity to textual distractions than visual ones. Additionally, we explored various mitigation strategies, such as prompt engineering, to counteract the impact of distractions. While these strategies improved solution accuracy, our analysis shows that there remain significant opportunities for improvement.
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。
