测试时提示法用于黑盒视觉-语言模型
Test-Time Hinting for Black-Box Vision-Language Models
AI总结：
本文提出测试时提示法，通过单次VLM调用提升性能，无需开放权重模型访问，适用于前沿闭源模型。方法通过轻量提示生成器预测提示，引导VLM避开常见错误模式，提升自然图像VQA基准的准确率。
摘要：
测试时缩放（TTS）方法在LLM中表现出色，但在视觉-语言模型（VLMs）中的应用仍较有限。现有VLM TTS方法大多需要开放权重模型访问或昂贵的重复采样，并主要在多模态数学和科学推理基准上评估，而非通用视觉理解任务。本文提出测试时提示法，通过单次VLM调用和仅需黑盒API访问即可提升VLM性能，广泛适用于前沿闭源模型。我们的方法受观察启发，即VLM错误倾向于聚集在重复失败模式周围。因此，我们训练了一个轻量级提示生成器模型，预测给定测试输入应添加哪种
英文摘要：
Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision-language models (VLMs) remains relatively underexplored. Existing VLM TTS methods largely require open-weight model access or expensive repeated sampling, and are evaluated primarily on multimodal mathematical and scientific reasoning benchmarks rather than general visual understanding tasks. In this paper, we propose Test-Time Hinting, a method that improves VLM performance via a single VLM call and requiring only black-box API access, which makes it broadly applicable to frontier closed-weight models. Our method is motivated by the observation that VLM errors tend to cluster around recurring failure patterns. We therefore train a lightweight hint generator model to predict, for a given test input, which "hint" should be prepended to the prompt, providing targeted contextual or procedural guidance that steers the VLM away from its characteristic failure modes. We show that Test-Time Hinting improves the accuracy of multiple closed-weight VLMs on natural-image VQA benchmarks and that these gains generalize to unseen benchmarks and VLMs without retraining the hint generator.
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。
