# Toward In-Context Teaching: Adapting Examples to Students' Misconceptions

arXiv: https://arxiv.org/abs/2405.04495 · HTML: https://mlsanity.com/paper/2405.04495/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker](https://mlsanity.com/paper/2306.00924/) (2023)
- [Eliciting Human Preferences with Language Models](https://mlsanity.com/paper/2310.11589/) (2023)
- [An Overview of Machine Teaching](https://mlsanity.com/paper/1801.05927/) (2018)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [Question Generation for Adaptive Education](https://mlsanity.com/paper/2106.04262/) (2021)
- [Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization](https://mlsanity.com/paper/2306.09299/) (2023)
- [Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning](https://mlsanity.com/paper/1903.03877/) (2019)
- [Extending rational models of communication from beliefs to actions](https://mlsanity.com/paper/2105.11950/) (2021)
- [Efficient Pragmatic Program Synthesis with Informative Specifications](https://mlsanity.com/paper/2204.02495/) (2022)

## Built on by (most cited first, 12 of 12)

- [Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors](https://mlsanity.com/paper/2407.09136/) (2024)
- [Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors](https://mlsanity.com/paper/2502.13311/) (2025)
- [Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors](https://mlsanity.com/paper/2510.11502/) (2025)
- [Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents](https://mlsanity.com/paper/2505.19997/) (2025)
- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation](https://mlsanity.com/paper/2508.19999/) (2025)
- [INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models](https://mlsanity.com/paper/2412.11388/) (2024)
- [Completion neq Collaboration: Scaling Collaborative Effort with Agents](https://mlsanity.com/paper/2510.25744/) (2025)
- [ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations](https://mlsanity.com/paper/2506.14200/) (2025)
- [SEFL: A Framework for Generating Synthetic Educational Assignment Feedback with LLM Agents](https://mlsanity.com/paper/2502.12927/) (2025)
- [Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank](https://mlsanity.com/paper/2602.02414/) (2026)
- [The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness](https://mlsanity.com/paper/2605.05648/) (2026)

## Abstract (arXiv)

When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what students already know and adapt their teaching to students' changing state of knowledge. There is increasing interest in using computational models, particularly large language models, as pedagogical tools. As students, language models in particular have shown a remarkable ability to adapt to new tasks given small numbers of examples. But how effectively can these models adapt as teachers to students of different types? To study this question, we introduce a suite of models and evaluation methods we call AdapT. AdapT has two components: (1) a collection of simulated Bayesian student models that can be used for evaluation of automated teaching methods; (2) a platform for evaluation with human students, to characterize the real-world effectiveness of these methods. We additionally introduce (3) AToM, a new probabilistic model for adaptive teaching that jointly infers students' past beliefs and optimizes for the correctness of future beliefs. In evaluations of simulated students across three learning domains (fraction arithmetic, English morphology, function learning), AToM systematically outperforms LLM-based and standard Bayesian teaching models. In human experiments, both AToM and LLMs outperform non-adaptive random example selection. Our results highlight both the difficulty of the adaptive teaching task and the potential of learned adaptive models for solving it.