EMNLP Findings2025
KELE: A Multi-Agent Framework for Structured Socratic Teaching with Large Language Models
Xian Peng, Pan Yuan, Dong Li, Junlong Cheng, Qin Fang, Zhi Liu
Abstract
Socratic teaching, known for its emphasis on heuristic questioning and deep thinking, has demonstrated significant advantages in promoting students' cognitive development. However, traditional Socratic teaching places high demands on teachers' expertise and real-time feedback capabilities, making it difficult to scale in large educational settings. Recent breakthroughs in large language models (LLMs) in natural language generation and dialogue comprehension offer the potential for automated Socratic teaching. In this paper, we propose Knowledge-Enlightened Learning Enhanced by LLMs (KELE), a novel multiagent framework for structured Socratic teaching with LLMs. KELE constructs a structured Socratic teaching rule system (SocRule) and a "consultant-teacher" multi-agent collaborative teaching mechanism, in which two LLMs respectively take charge of teaching planning and execution, ensuring a logically coherent and hierarchically structured Socratic teaching process. We also construct SocratDataset, a structured Socratic teaching dataset covering 34 teaching strategies and over 42,000 dialogue turns, and train SocratTeachLLM, a specialized LLM for Socratic teaching tasks. Additionally, we build a comprehensive Socratic teaching quality evaluation system for LLMs, covering 9 dimensions from single-turn dialogue to multiturn teaching processes. Experimental results show that SocratTeachLLM significantly outperforms GPT-4o, which has a much larger parameter size, across all Socratic teaching capabilities. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on8
- Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question AnsweringPan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu et al.NeurIPS 2022 · 2,727 citations
- Make Your LLM Fully Utilize the ContextShengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng et al.NeurIPS 2024 · 212 citations
- A Closer Look at the Limitations of Instruction TuningSreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Ramaneswaran S. et al.ICML 2024 · 90 citations
- MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning ProblemsJakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha et al.EMNLP Findings 2023 · 39 citations
- CLASS: A Design Framework for Building Intelligent Tutoring Systems Based on Learning Science principlesShashank Sonkar, Naiming Liu, Debshila Basu Mallick, Richard G. BaraniukEMNLP Findings 2023 · 35 citations
Related papers
- SocraticLM: Exploring Socratic Personalized Teaching with Large Language ModelsJiayu Liu, Zhenya Huang, Tong Xiao, Jing Sha et al.NeurIPS 2024 · 65 citations
- MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt OptimizationJian Zhang, Zhangqi Wang, Haiping Zhu, Kangda Cheng et al.AAAI 2026 · 9 citations
- MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM IdeationXinping Lei, Tong Zhou, Yubo Chen, Kang Liu et al.EMNLP Findings 2025
- Socratic-Geo: Synthetic Data Generation and Cross-Modal Geometric Reasoning via Multi-Agent InteractionZhengbo Jiao, Zifan Zhang, Shaobo Wang, Wei Wang et al.CVPR 2026
- Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning StylesDebdeep Sanyal, Agniva Maiti, Umakanta Maharana, Dhruv Kumar et al.EMNLP 2025 · 1 citation
