探究大型语言模型在解释性对话中的共建行为
Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues
AI总结：
本研究探究LLMs在共建解释对话中作为解释者的能力，通过用户研究评估其共建行为对解释接受者理解和参与的影响，发现LLMs能通过提问促进参与，但监控和调整解释的能力有限。
摘要：
生成能被解释接受者理解的解释是可解释人工智能的精髓。由于理解取决于解释接受者的背景和需求，近期研究关注共建解释对话，其中解释者持续监控解释接受者的理解并动态调整其解释。我们探究了大型语言模型（LLMs）作为解释者参与共建解释对话的能力。具体而言，我们开展了一项用户研究，解释接受者在两种设置下与LLM互动，其中一种涉及指示LLM以共建方式解释主题。我们评估了解释接受者在对话前后的理解情况，以及他们对LLM共建行为的感知。结果表明，LLMs表现出一些共建行为，如提出验证问题，这促进了解释接受者的参与并可能提升对主题的理解。然而，它们有效监控当前理解并据此搭建解释的能力仍然有限。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
