# Representational Alignment Supports Effective Machine Teaching

arXiv: https://arxiv.org/abs/2406.04302 · HTML: https://mlsanity.com/paper/2406.04302/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 69 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [Human alignment of neural network representations](https://mlsanity.com/paper/2211.01201/) (2022)
- [Reasoning About Pragmatics with Neural Listeners and Speakers](https://mlsanity.com/paper/1604.00562/) (2016)
- [An Overview of Machine Teaching](https://mlsanity.com/paper/1801.05927/) (2018)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [Inferring Rewards from Language in Context](https://mlsanity.com/paper/2204.02515/) (2022)
- [Learning Language Games through Interaction](https://mlsanity.com/paper/1606.02447/) (2016)
- [Iterative Machine Teaching](https://mlsanity.com/paper/1705.10470/) (2017)
- [Learning Rewards from Linguistic Feedback](https://mlsanity.com/paper/2009.14715/) (2020)
- [Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning](https://mlsanity.com/paper/2402.17930/) (2024)
- [Alignment with human representations supports robust few-shot learning](https://mlsanity.com/paper/2301.11990/) (2023)
- [A mathematical theory of cooperative communication](https://mlsanity.com/paper/1910.02822/) (2019)
- [How to talk so AI will learn: Instructions, descriptions, and autonomy](https://mlsanity.com/paper/2206.07870/) (2022)
- [Towards Black-box Iterative Machine Teaching](https://mlsanity.com/paper/1710.07742/) (2017)
- [The Teaching Dimension of Linear Learners](https://mlsanity.com/paper/1512.02181/) (2015)
- [Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning](https://mlsanity.com/paper/1903.03877/) (2019)
- [An Optimal Control Approach to Sequential Machine Teaching](https://mlsanity.com/paper/1810.06175/) (2018)
- [Iterative Teaching by Label Synthesis](https://mlsanity.com/paper/2110.14432/) (2021)
- [Nonparametric Iterative Machine Teaching](https://mlsanity.com/paper/2306.03007/) (2023)
- [Iterative Classroom Teaching](https://mlsanity.com/paper/1811.03537/) (2018)
- [Iterative Teaching by Data Hallucination](https://mlsanity.com/paper/2210.17467/) (2022)
- [Can Humans Do Less-Than-One-Shot Learning?](https://mlsanity.com/paper/2202.04670/) (2022)
- [Learning Human-like Representations to Enable Learning Human Values](https://mlsanity.com/paper/2312.14106/) (2023)
- [Teacher Improves Learning by Selecting a Training Subset](https://mlsanity.com/paper/1802.08946/) (2018)
- [Concept Alignment as a Prerequisite for Value Alignment](https://mlsanity.com/paper/2310.20059/) (2023)
- [Dimensions of Disagreement: Unpacking Divergence and Misalignment in Cognitive Science and Artificial Intelligence](https://mlsanity.com/paper/2310.12994/) (2023)

## Built on by (most cited first, 3 of 3)

- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [When Should We Orchestrate Multiple Agents?](https://mlsanity.com/paper/2503.13577/) (2025)
- [Revisiting Rogers' Paradox in the Context of Human-AI Interaction](https://mlsanity.com/paper/2501.10476/) (2025)

## Abstract (arXiv)

A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world. In this work, we introduce a new controlled experimental setting, GRADE, to study pedagogy and representational alignment. We use GRADE through a series of machine-machine and machine-human teaching experiments to characterize a utility curve defining a relationship between representational alignment, teacher expertise, and student learning outcomes. We find that improved representational alignment with a student improves student learning outcomes (i.e., task accuracy), but that this effect is moderated by the size and representational diversity of the class being taught. We use these insights to design a preliminary classroom matching procedure, GRADE-Match, that optimizes the assignment of students to teachers. When designing machine teachers, our results suggest that it is important to focus not only on accuracy, but also on representational alignment with human learners.