一篇新论文探讨了大型语言模型在将二维结构化数据转换为一维序列时面临的挑战。研究人员发现，这种“序列化摩擦”会阻碍模型在矩阵转置和康威生命游戏等任务上的表现。一种保留二维布局的增强视觉通路，其性能显著优于纯文本通路，这表明保持空间结构对于这类任务至关重要。 AI
影响 强调了当前大型语言模型在处理结构化二维数据时的潜在输入处理局限性，并指明了改进方向。
排序理由 学术论文，详细介绍了新概念（“序列化摩擦”）和实验结果。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.27272v1 Announce Type: cross Abstract: Large language models (LLMs) conventionally process structured inputs as 1D token sequences. While natural for prose, such linearization may introduce additional representational burden for tasks whose computation depends directly…
Large language models (LLMs) conventionally process structured inputs as 1D token sequences. While natural for prose, such linearization may introduce additional representational burden for tasks whose computation depends directly on explicit 2D structure, because row--column ali…