研究人员开发了一种用于立场检测的多智能体推理框架，旨在通过综合多个AI智能体的解释来提高准确性，而不是依赖简单的标签聚合。这种管理者-工作者架构根据输入复杂性自适应地分配智能体，每个工作者提供仅推理的分析。该框架在具有挑战性的隐式和上下文相关立场检测任务上取得了显著的进步，在COVID-19 Stance和SemEval-2016等数据集上获得了高Macro-F1分数。 AI
影响 增强了LLM在细微文本分析方面的能力，可能改进需要理解作者意图的应用。
排序理由 该集群包含一篇详细介绍立场检测新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.11609v1 Announce Type: new Abstract: Stance detection requires identifying an author's position toward a target, often from short-form texts where stance is implicit, indirect, or rhetorically framed. Although large language models (LLMs) achieve strong performance on …
Stance detection requires identifying an author's position toward a target, often from short-form texts where stance is implicit, indirect, or rhetorically framed. Although large language models (LLMs) achieve strong performance on this task, single-pass prompting can be brittle …