Deployed multimodal systems can fail in ways that evaluators did not anticipate. In order to find these failures before deployment, we introduce MultiMon, a system that automatically identifies systematic failures -- generalizable, natural-language descriptions of patterns of model failures. To uncover systematic failures, MultiMon scrapes a corpus for examples of erroneous agreement: inputs that produce the same output, but should not. It then prompts a language model (e.g., GPT-4) to find systematic patterns of failure and describe them in natural language. We use MultiMon to find 14 systematic failures (e.g., "ignores quantifiers") of the CLIP text-encoder, each comprising hundreds of distinct inputs (e.g., "a shelf with a few/many books"). Because CLIP is the backbone for most state-of-the-art multimodal systems, these inputs produce failures in Midjourney 5.1, DALL-E, VideoFusion, and others. MultiMon can also steer towards failures relevant to specific use cases, such as self-driving cars. We see MultiMon as a step towards evaluation that autonomously explores the long tail of potential system failures. Code for MULTIMON is available at https://github.com/tsb0601/MultiMon.

翻译：已部署的多模态系统可能会以评估者未曾预料的方式发生故障。为了在部署前发现这些故障，我们引入了MultiMon系统，该系统可自动识别系统性故障——即模型故障模式的可泛化自然语言描述。为揭示系统性故障，MultiMon从语料库中抓取错误一致性样本：即输入相同但本应产生不同输出的案例。随后，它通过提示语言模型（如GPT-4）发现系统性的故障模式，并用自然语言进行描述。我们利用MultiMon发现了CLIP文本编码器的14种系统性故障（例如“忽略量词”），每种故障包含数百个不同的输入（如“一个有一本/许多书的书架”）。由于CLIP是当前最先进多模态系统的主要骨干模型，这些输入会导致Midjourney 5.1、DALL-E、VideoFusion等系统产生故障。MultiMon还能针对特定应用场景（如自动驾驶）定向挖掘相关故障。我们认为MultiMon是迈向自主探索潜在系统故障长尾分布的评估方法的重要一步。MultiMon代码已开源至https://github.com/tsb0601/MultiMon。