ReadBench：衡量视觉语言模型的密集文本视觉阅读能力
ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models
AI总结：
ReadBench是一个新基准，通过将文本上下文转为图像来评估VLMs的密集文本阅读能力，发现长文本性能显著下降，而分辨率影响甚微。
摘要：
近期大型视觉语言模型（VLMs）的进步极大地增强了它们联合处理文本和图像的能力。然而，尽管已有大量基准测试评估视觉理解（例如图表、配色方案、OCR任务等），但对VLMs有效阅读和推理文本丰富图像的能力评估仍然有限。为填补这一空白，我们引入了ReadBench，一个专门设计用于评估VLMs阅读理解能力的多模态基准。ReadBench将既有纯文本基准中的上下文转置为文本图像，同时保持文本提示和问题不变。使用ReadBench评估领先的VLMs，我们发现短文本图像输入上存在虽小但明显的性能下降，而在较长、多页上下文上性能急剧下降。我们的实验进一步揭示，文本分辨率对多模态性能的影响可忽略不计。这些发现凸显了VLMs需要改进之处，特别是它们对视觉呈现的广泛文本内容的推理能力，这一能力对实际应用至关重要。ReadBench可在https://github.com/answerdotai/ReadBench获取。
英文摘要：
Recent advancements in Large Vision-Language Models (VLMs), have greatly enhanced their capability to jointly process text and images. However, despite extensive benchmarks evaluating visual comprehension (e.g., diagrams, color schemes, OCR tasks...), there is limited assessment of VLMs' ability to read and reason about text-rich images effectively. To fill this gap, we introduce ReadBench, a multimodal benchmark specifically designed to evaluate the reading comprehension capabilities of VLMs. ReadBench transposes contexts from established text-only benchmarks into images of text while keeping textual prompts and questions intact. Evaluating leading VLMs with ReadBench, we find minimal-but-present performance degradation on short, text-image inputs, while performance sharply declines for longer, multi-page contexts. Our experiments further reveal that text resolution has negligible effects on multimodal performance. These findings highlight needed improvements in VLMs, particularly their reasoning over visually presented extensive textual content, a capability critical for practical applications. ReadBench is available at https://github.com/answerdotai/ReadBench .
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。
