惊人的脆弱性：评估与解决多模态基础模型中的提示不稳定性问题
Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models
AI总结：
本文针对多模态基础模型存在的提示不稳定性问题，提出基于相似度过滤的接地提示扰动数据增强重训练方法，可有效提升模型扰动场景下的准确率与稳定性，增强其通用推理能力。
摘要：
诸如OFASys之类的多模态基础模型（MFMs）展现出仅通过文本提示即可解锁图像、视频、音频等复杂数据分析的潜力。但即便文本输入与训练分布仅存在微小差异，其性能也会出现下降，考虑到这类模型使用特定模态数据为文本输入做“接地”，这一现象十分出人意料。本研究证实，提示不稳定性是多模态基础模型面临的一大核心问题，会导致所有模态的性能出现一致性下降，但通过增强数据开展额外训练可缓解该不稳定性。我们评估了多种接地提示扰动方法，即生成扰动后基于与文本和/或模态数据的相似度完成过滤。在使用增强数据重新训练模型后我们发现，无论处于何种扰动条件，模型在扰动测试数据上的准确率均有所提升，性能也更稳定，说明该数据增强策略可帮助模型更有效地应对域偏移。误差分析显示，各域的性能提升模式一致，表明基于提示扰动的重训练有助于提升多模态基础模型的通用推理能力。
英文摘要：
Multimodal foundation models (MFMs) such as OFASys show the potential to unlock analysis of complex data such as images, videos, and audio data via text prompts alone. However, their performance may suffer in the face of text input that differs even slightly from their training distribution, which is surprising considering the use of modality-specific data to "ground" the text input. This study demonstrates that prompt instability is a major concern for MFMs, leading to a consistent drop in performance across all modalities, but that instability can be mitigated with additional training with augmented data. We evaluate several methods for grounded prompt perturbation, where we generate perturbations and filter based on similarity to text and/or modality data. After re-training the models on the augmented data, we find improved accuracy and more stable performance on the perturbed test data regardless of perturbation condition, suggesting that the data augmentation strategy helps the models handle domain shifts more effectively. In error analysis, we find consistent patterns of performance improvement across domains, suggesting that retraining on prompt perturbations tends to help general reasoning capabilities in MFMs.
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。
