Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark

TL;DR

This paper introduces Pedagogy-R1, a reasoning model adapted for educational settings, featuring a new training pipeline, an educational benchmark, and a prompting strategy to enhance pedagogical coherence and evaluate teaching-related skills.

Contribution

The paper presents Pedagogy-R1, a novel framework that aligns large reasoning models with pedagogical tasks through innovative training, evaluation, and prompting methods.

Findings

Pedagogy-R1 demonstrates improved pedagogical reasoning over baseline models.

The Well-balanced Educational Benchmark effectively evaluates multiple teaching-related skills.

The Chain-of-Pedagogy prompting enhances the model's ability to generate teacher-like reasoning.

Abstract

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.