English(EN) GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents

新的GDP.pdf基准揭示前沿模型在处理专业文档时遇到困难

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-13 07:44

一个名为GDP.pdf的新基准已被发布，用于评估在专业文档上的多模态推理能力。该基准包含由专业人士创建的100个问题-文档对，旨在挑战前沿多模态模型。在测试中，表现最好的模型仅达到15%的通过率，表明AI在理解和推理复杂专业文档方面的能力仍有很大提升空间。 AI

影响突显了当前多模态模型在理解真实世界专业文档方面的局限性，表明需要改进推理和地面能力。

排序理由该集群描述了一个用于评估AI模型在专业文档上表现的新学术基准。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群描述了一个用于评估AI模型在专业文档上表现的新学术基准。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 53 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Suhaas Garre, Emily Ritchie, Sushant Mehta, Edwin Chen · 2026-07-14 04:00

GDP.pdf: 在专业PDF文档上进行基于现实的多模态推理基准测试

arXiv:2607.11192v1 Announce Type: new Abstract: A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabi…
arXiv cs.CV TIER_1 English(EN) · Edwin Chen · 2026-07-13 07:44

GDP.pdf: 专业PDF文档上的接地多模态推理基准测试

A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabilities in isolation: OCR, layout analysis, chart…