English(EN) Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

新GPlan框架增强基于LLM的时空推荐

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-27 07:27

研究人员开发了一个名为GPlan的新框架，以改进生成时空意图序列推荐（GSISR）。该框架解决了使用大型语言模型进行实际服务推荐时的高推理延迟和上下文不匹配计划的挑战。GPlan利用渐进式隐式CoT蒸馏将LLM推理压缩到更小的模型中，并利用时空反事实DPO增强对时空上下文的敏感性并减少不可行计划。实验表明，GPlan提高了序列连贯性和上下文响应性。 AI

影响这项研究提供了一种使基于LLM的推荐更高效、更具上下文相关性的方法，有望改善服务应用中的用户体验。

排序理由该集群包含一篇详细介绍特定AI任务新框架和技术的学术论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

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

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Sicong Wang, Ruiting Dong, Yue Liu, Bowen Zheng, Jun Meng, Jie Li, Shuaijun Guo, Yu Gu, Fanyi Di, Xin Li · 2026-05-29 04:00

Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

arXiv:2605.28888v1 Announce Type: cross Abstract: Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated service recommendations, we focus on the task of Generative Spatiote…
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Xin Li · 2026-05-27 07:27

Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated service recommendations, we focus on the task of Generative Spatiotemporal Intent Sequence Recommendation (GSISR), whi…

报道来源 [2]

Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap

相关实体

相关话题