可视化在多模态大语言模型处理网络数据任务中对其决策产生偏差
Visualization Biases MLLM's Decision Making in Network Data Tasks
AI总结：
本文研究可视化对多模态大语言模型判断网络中桥接存在性的影响，发现可视化虽能提高模型置信度，却会引入与真实网络结构无关的强烈判断偏差，提醒生成式人工智能应用需谨慎使用可视化以防幻觉。
摘要：
我们评估了可视化如何影响多模态大语言模型（MLLM）对网络中是否存在桥接的判断。我们表明，与理论上可帮助回答问题的结构化文本输入相比，加入可视化会提高模型的置信度。另一方面，我们观察到标准可视化技术会产生强烈偏差，使模型倾向于接受或否定桥接的存在——无论网络中是否真的存在桥接。虽然我们的结果表明，加入可视化技术可以在不损害模型自我报告置信度的情况下有效影响 MLLM 的判断，但这些结果也意味着，从业者必须谨慎允许用户在生成式人工智能应用中加入可视化，以避免产生不期望的幻觉。
英文摘要：
We evaluate how visualizations can influence the judgment of MLLMs about the presence or absence of bridges in a network. We show that the inclusion of visualization improves confidence over a structured text-based input that could theoretically be helpful for answering the question. On the other hand, we observe that standard visualization techniques create a strong bias towards accepting or refuting the presence of a bridge -- independently of whether or not a bridge actually exists in the network. While our results indicate that the inclusion of visualization techniques can effectively influence the MLLM's judgment without compromising its self-reported confidence, they also imply that practitioners must be careful of allowing users to include visualizations in generative AI applications so as to avoid undesired hallucinations.
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。
