EduDial: Constructing a Large-scale Multi-turn Teacher–Student Dialogue Corpus

Shouang Wei, Min Zhang, Xin Alex Lin, Bo Jiang, Zhongxiang Dai, Kun Kuang

Keywords: Large Language Models; Multi-turn Teacher-Student Dialogue;Intelligent Education

Abstract: Recently, several multi-turn dialogue benchmarks have been proposed to evaluate the conversational abilities of large language models (LLMs). As LLMs are increasingly recognized as a key technology for advancing intelligent education, owing to their ability to deeply understand instructional contexts and provide personalized guidance, the construction of dedicated teacher-student dialogue benchmarks has become particularly important. To this end, we present EduDial, a comprehensive multi-turn teacher-student dialogue dataset. EduDial covers 345 core knowledge points and consists of 34,250 dialogue sessions generated through interactions between teacher and student agents. Its design is guided by Bloom’s taxonomy of educational objectives and incorporates ten questioning strategies—including situational questioning, zone of proximal development (ZPD) questioning, and metacognitive questioning—thus better capturing authentic classroom interactions. Furthermore, we design differentiated teaching strategies for students at different cognitive levels, thereby providing more targeted teaching guidance. Building on EduDial, we further develop EduDial-LLM 32B via training and propose an 11-dimensional evaluation framework that systematically measures the teaching abilities of LLMs, encompassing both overall teaching quality and content quality. Experiments on 17 mainstream LLMs reveal that most models struggle in student-centered teaching scenarios, whereas our EduDial-LLM achieves significant gains, consistently outperforming all baselines across all metrics.

Primary Area: datasets and benchmarks

Submission Number: 3406