PulseAugur
实时 12:21:20
English(EN) GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

GEM 框架通过图增强专家和 ReAct 代理提升对话状态跟踪能力

研究人员开发了 GEM,一个用于对话状态跟踪的新颖框架,该框架结合了图增强混合专家模型和 ReAct 代理。这种方法动态地路由到专门的专家之间,包括用于对话结构的图神经网络和 T5-Small 编码器-解码器,并由路由器协调。对于复杂任务,ReAct 代理执行结构化推理,在 MultiWOZ 2.2 上实现了 65.19% 的联合目标准确率,显著优于现有的 LLM 方法和最先进的方法。 AI

影响 这种方法可以提高对话系统在复杂、多领域对话中的准确性和效率。

排序理由 该集群包含一篇 arXiv 预印本,详细介绍了一种新的对话状态跟踪方法。

在 arXiv cs.CL 阅读 →

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

GEM 框架通过图增强专家和 ReAct 代理提升对话状态跟踪能力

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Ziqi Zhu, Adithya Suresh, Tomal Deb, Iman Abbasnejad ·

    GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

    arXiv:2605.04449v1 Announce Type: new Abstract: Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We present GEM (G…

  2. arXiv cs.CL TIER_1 English(EN) · Iman Abbasnejad ·

    GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

    Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We present GEM (Graph-Enhanced Mixture-of-Experts), a novel frame…