Papers › From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using...

From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning

21 May 2025arXiv:2505.15607archive 2025-07-28

David Dinucu-Jianu, Jakub Macina, Nico Daheim, Ido Hakimi, Iryna Gurevych, Mrinmaya Sachan

Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withholding answers. To mitigate this, we propose an online reinforcement learning (RL)-based alignment framework that can quickly adapt LLMs into effective tutors using simulated student-tutor interactions by emphasizing pedagogical quality and guided problem-solving over simply giving away answers. We use our method to train a 7B parameter tutor model without human annotations which reaches similar performance to larger proprietary models like LearnLM. We introduce a controllable reward weighting to balance pedagogical support and student solving accuracy, allowing us to trace the Pareto frontier between these two objectives. Our models better preserve reasoning capabilities than single-turn SFT baselines and can optionally enhance interpretability through thinking tags that expose the model's instructional planning.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

eth-lre/pedagogicalrl officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SFT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections