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

• URL: http://arxiv.org/abs/2505.18467v1
• Date: Sat, 24 May 2025 02:18:35 GMT
• Title: Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark
• Authors: Unggi Lee, Jaeyong Lee, Jiyeong Bae, Yeil Jeong, Junbo Koh, Gyeonggeon Lee, Gunho Lee, Taekyung Ahn, Hyeoncheol Kim,
• Abstract summary: Large reasoning models (LRMs) show strong performance in structured domains such as mathematics and programming.<n>LRMs often lack pedagogical coherence and realistic teaching behaviors.<n>We introduce Pedagogy-R1, a framework that adapts LRMs for classroom use through three innovations.
• Score: 6.024228339466189
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Benchmarking the Pedagogical Knowledge of Large Language Models [4.417539128489408]
  This paper introduces The Pedagogy Benchmark, a novel dataset designed to evaluate large language models on their pedagogical knowledge.<n>These benchmarks are built on a carefully curated set of questions sourced from professional development exams for teachers.<n>We report results for 97 models, with accuracies spanning a range from 28% to 89% on the pedagogical knowledge questions.
  arXiv  Detail & Related papers  (2025-06-23T14:49:01Z)
• On the development of an AI performance and behavioural measures for teaching and classroom management [29.68201271068342]
  This paper presents a two-year research project focused on developing AI-driven measures to analyze classroom dynamics.<n>Key outcomes include a curated audio-visual dataset, novel behavioral measures, and a proof-of-concept teaching review dashboard.
  arXiv  Detail & Related papers  (2025-06-11T04:52:50Z)
• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [82.43575191712726]
  We introduce a fine-grained analytic framework to dissect the impact ofReinforcement learning on reasoning.<n>Our framework specifically investigates key elements that have been hypothesized to benefit from RL training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning [76.09281171131941]
  Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy.<n>We propose an online reinforcement learning (RL)-based alignment framework that can quickly adapt LLMs into effective tutors.
  arXiv  Detail & Related papers  (2025-05-21T15:00:07Z)
• RM-R1: Reward Modeling as Reasoning [81.50471199906738]
  Reasoning Reward Models (ReasRMs) formulate reward modeling as a reasoning task.<n>We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1.<n>Our models achieve state-of-the-art performance across three reward model benchmarks on average.
  arXiv  Detail & Related papers  (2025-05-05T06:11:12Z)
• EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework [9.76455227840645]
  Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging.<n>We introduce EducationQ, a multi-agent dialogue framework that efficiently assesses teaching capabilities through simulated dynamic educational scenarios.
  arXiv  Detail & Related papers  (2025-04-21T07:48:20Z)
• Fine-Tuning Large Language Models for Educational Support: Leveraging Gagne's Nine Events of Instruction for Lesson Planning [5.022835754140817]
  This study investigates how large language models (LLMs) can enhance teacher preparation by incorporating them with Gagne's Nine Events of Instruction.<n>The research starts with creating a comprehensive dataset based on math curriculum standards and Gagne's instructional events.<n>The second method uses specialized datasets to fine-tune open-source models, enhancing their educational content generation and analysis capabilities.
  arXiv  Detail & Related papers  (2025-03-12T11:22:13Z)
• MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors [76.1634959528817]
  We present MathTutorBench, an open-source benchmark for holistic tutoring model evaluation.<n>MathTutorBench contains datasets and metrics that broadly cover tutor abilities as defined by learning sciences research in dialog-based teaching.<n>We evaluate a wide set of closed- and open-weight models and find that subject expertise, indicated by solving ability, does not immediately translate to good teaching.
  arXiv  Detail & Related papers  (2025-02-26T08:43:47Z)
• Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors [7.834688858839734]
  We investigate whether current state-of-the-art large language models (LLMs) are effective as AI tutors.<n>We propose a unified evaluation taxonomy with eight pedagogical dimensions based on key learning sciences principles.<n>We release MRBench - a new evaluation benchmark containing 192 conversations and 1,596 responses from seven state-of-the-art LLM-based and human tutors.
  arXiv  Detail & Related papers  (2024-12-12T16:24:35Z)
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval [83.79667141681418]
  Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR) We propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. We show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.
  arXiv  Detail & Related papers  (2023-01-27T22:04:37Z)
• Teachers' perspective on fostering computational thinking through educational robotics [0.6410282200111983]
  The Creative Problem Solving Model (CCPS) can be employed to improve the design of educational robotics learning activities. The objective of the present study is to validate the model with teachers, specifically considering how they may employ the model in their own practices. Teachers found the CCPS model useful to foster skills but could not recognise the impact of specific intervention methods on CT-related cognitive processes.
  arXiv  Detail & Related papers  (2021-05-11T12:31:44Z)
• Dual Policy Distillation [58.43610940026261]
  Policy distillation, which transfers a teacher policy to a student policy, has achieved great success in challenging tasks of deep reinforcement learning. In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2020-06-07T06:49:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.