测试大模型在解释对话中动态调整能力，发现能提问促理解但监控仍弱。
Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues
- 让大模型通过提问验证理解，动态调整解释内容。
- 对话后理解提升17%，但模型对理解状态的判断准确率仅63%。
- 适合研究人机交互与可解释AI，尤其关注对话式教学场景。
生成被理解的解释是可解释人工智能的核心。由于理解依赖于解释对象的背景和需求，近期研究聚焦于协同构建型解释对话，即解释者持续监测解释对象的理解状况并动态调整解释内容。本文研究大语言模型（LLMs）作为解释者在协同构建型解释对话中的表现。我们开展用户研究，让解释对象在两种情境下与大模型互动，其中一种情境下要求模型以协同构建方式解释特定主题。评估对话前后解释对象的理解程度，以及对模型协同行为的感知。结果显示，大模型表现出一定协同行为，如提出验证性问题，促进解释对象参与并提升理解。然而，其有效监测当前理解状态并相应支撑解释的能力仍有限。
原文摘要 · Abstract (English)
The ability to generate explanations that are understood by explainees is the quintessence of explainable artificial intelligence. Since understanding depends on the explainee's background and needs, recent research focused on co-constructive explanation dialogues, where an explainer continuously monitors the explainee's understanding and adapts their explanations dynamically. We investigate the ability of large language models (LLMs) to engage as explainers in co-constructive explanation dialogues. In particular, we present a user study in which explainees interact with an LLM in two settings, one of which involves the LLM being instructed to explain a topic co-constructively. We evaluate the explainees' understanding before and after the dialogue, as well as their perception of the LLMs' co-constructive behavior. Our results suggest that LLMs show some co-constructive behaviors, such as asking verification questions, that foster the explainees' engagement and can improve understanding of a topic. However, their ability to effectively monitor the current understanding and scaffold the explanations accordingly remains limited.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。