Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark
This work addresses the need for more educationally aligned AI models for teachers and students, though it appears incremental as it builds on existing reasoning models with specific adaptations.
The paper tackled the problem of large reasoning models lacking pedagogical coherence for classroom use by introducing Pedagogy-R1, a framework that adapts these models through innovations like distillation, a balanced benchmark, and a prompting strategy, resulting in the first systematic assessment of their pedagogical strengths and limitations.
Recent advances in large reasoning models (LRMs) show strong performance in structured domains such as mathematics and programming; however, they often lack pedagogical coherence and realistic teaching behaviors. To bridge this gap, we introduce Pedagogy-R1, a framework that adapts LRMs for classroom use through three innovations: (1) a distillation-based pipeline that filters and refines model outputs for instruction-tuning, (2) the Well-balanced Educational Benchmark (WBEB), which evaluates performance across subject knowledge, pedagogical knowledge, tracing, essay scoring, and teacher decision-making, and (3) a Chain-of-Pedagogy (CoP) prompting strategy for generating and eliciting teacher-style reasoning. Our mixed-method evaluation combines quantitative metrics with qualitative analysis, providing the first systematic assessment of LRMs' pedagogical strengths and limitations.