研究人员推出了一项名为ConflictScore的新指标，旨在评估语言模型在处理其基础文档中的冲突信息方面的能力。与仅检查支持或矛盾的现有指标不同，ConflictScore量化了对支持和矛盾证据的承认程度。该指标以及一个名为ConflictBench的新基准旨在识别过度自信的声明并提高模型的真实性。 AI
影响 该指标通过直接解决AI系统在导航和呈现冲突信息方面的能力，有望带来更真实可靠的AI系统。
排序理由 该集群描述了一篇介绍用于评估语言模型的新颖指标和基准的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.26437v1 Announce Type: cross Abstract: Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting and contradicting evidence coexist. We introduce Co…
Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting and contradicting evidence coexist. We introduce ConflictScore, a novel metric that quantifies how we…