# TeachLM: Post-Training LLMs for Education Using Authentic Learning Data

arXiv: https://arxiv.org/abs/2510.05087 · HTML: https://mlsanity.com/paper/2510.05087/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 78 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems](https://mlsanity.com/paper/2305.14536/) (2023)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2401.16745/) (2024)
- [The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues](https://mlsanity.com/paper/2205.07540/) (2022)
- [Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach](https://mlsanity.com/paper/2407.12687/) (2024)
- [Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise](https://mlsanity.com/paper/2410.03017/) (2024)
- [DARWIN Series: Domain Specific Large Language Models for Natural Science](https://mlsanity.com/paper/2308.13565/) (2023)
- [GPT-3-driven pedagogical agents for training children's curious question-asking skills](https://mlsanity.com/paper/2211.14228/) (2022)
- [Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents](https://mlsanity.com/paper/2505.19997/) (2025)
- [The Teacher-Student Chatroom Corpus](https://mlsanity.com/paper/2011.07109/) (2020)
- [On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation](https://mlsanity.com/paper/2410.00863/) (2024)
- [Evaluating Gemini in an arena for learning](https://mlsanity.com/paper/2505.24477/) (2025)
- [AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions](https://mlsanity.com/paper/2508.16402/) (2025)
- [Which Type of Students can LLMs Act? Investigating Authentic Simulation with Graph-based Human-AI Collaborative System](https://mlsanity.com/paper/2502.11678/) (2025)
- [Assessing the efficacy of large language models in generating accurate teacher responses](https://mlsanity.com/paper/2307.04274/) (2023)

## Built on by (most cited first, 9 of 9)

- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks](https://mlsanity.com/paper/2604.18660/) (2026)
- [Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues](https://mlsanity.com/paper/2605.30051/) (2026)
- [Reasoning Trajectories for Socratic Debugging of Student Code: From Misconceptions to Contradictions and Updated Beliefs](https://mlsanity.com/paper/2511.00371/) (2025)
- [Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning](https://mlsanity.com/paper/2604.06385/) (2026)
- [EvalConvoLearn: An Open-Source Framework for Evaluating Grounded Learner Simulations in Tutoring Conversations](https://mlsanity.com/paper/2608.07497/) (2026)
- [ADE: Agentic Data Evolution Framework for Human-Centered Objectives](https://mlsanity.com/paper/2608.23719/) (2026)
- [Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing](https://mlsanity.com/paper/2609.28026/) (2026)
- [RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning](https://mlsanity.com/paper/2610.13399/) (2026)

## Abstract (arXiv)

The promise of generative AI to revolutionize education is constrained by the pedagogical limits of large language models (LLMs). A major issue is the lack of access to high-quality training data that reflect the learning of actual students. Prompt engineering has emerged as a stopgap, but the ability of prompts to encode complex pedagogical strategies in rule-based natural language is inherently limited. To address this gap we introduce TeachLM - an LLM optimized for teaching through parameter-efficient fine-tuning of state-of-the-art models. TeachLM is trained on a dataset comprised of 100,000 hours of one-on-one, longitudinal student-tutor interactions maintained by Polygence, which underwent a rigorous anonymization process to protect privacy. We use parameter-efficient fine-tuning to develop an authentic student model that enables the generation of high-fidelity synthetic student-tutor dialogues. Building on this capability, we propose a novel multi-turn evaluation protocol that leverages synthetic dialogue generation to provide fast, scalable, and reproducible assessments of the dialogical capabilities of LLMs. Our evaluations demonstrate that fine-tuning on authentic learning data significantly improves conversational and pedagogical performance - doubling student talk time, improving questioning style, increasing dialogue turns by 50%, and greater personalization of instruction.