研究人员推出了一种名为嵌入式一致性（EBA）的新颖方法，用于增强大型语言模型在开放式生成任务中的自洽性。该技术利用表示空间的几何特性，对采样生成的文本进行聚类，以估计语义兼容性，而不是依赖于精确匹配。EBA在数学推理、代码生成和摘要等任务上的表现优于随机选择和其他基于LLM的评估方法。 AI
影响 该方法有望提高LLM在复杂生成任务中输出的可靠性和准确性。
排序理由 该集群包含一篇详细介绍改进LLM性能新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.12003v1 Announce Type: new Abstract: Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categorical outputs. …
Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categorical outputs. In this work, we study self-consistency in open-…