研究人员推出了TransitLM，这是一个用于无地图公交路线生成的新型数据集和基准测试。该大规模数据集包含来自中国四个城市的1300多万条公交记录，使大型语言模型能够在不依赖传统地图基础设施的情况下规划路线。实验表明，在TransitLM上训练的LLM可以准确生成有效的路线，并隐式地将GPS坐标映射到站点，展示了端到端、数据驱动的路线规划潜力。 AI
影响 使LLM能够在没有传统地图数据的情况下执行复杂的路线规划任务，从而可能改进导航和物流应用。
排序理由 该集群描述了在研究论文中发布的新数据集和基准测试。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.22355v1 Announce Type: new Abstract: Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale datase…
Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning reco…
TransitLM dataset enables end-to-end transit route planning using large language models trained on structured transit data, eliminating the need for traditional map-based approaches.