# Towards Human-AI Mutual Learning: A New Research Paradigm

arXiv: https://arxiv.org/abs/2405.04687 · HTML: https://mlsanity.com/paper/2405.04687/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 38 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 6 of 6)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [The Expressive Power of Neural Networks: A View from the Width](https://mlsanity.com/paper/1709.02540/) (2017)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Advancing Human-AI Complementarity: The Impact of User Expertise and Algorithmic Tuning on Joint Decision Making](https://mlsanity.com/paper/2208.07960/) (2022)

## Built on by (most cited first, 2 of 2)

- [ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry](https://mlsanity.com/paper/2507.16280/) (2025)
- [Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs](https://mlsanity.com/paper/2605.22971/) (2026)

## Abstract (arXiv)

This paper describes a new research paradigm for studying human-AI collaboration, named "human-AI mutual learning", defined as the process where humans and AI agents preserve, exchange, and improve knowledge during human-AI collaboration. We describe relevant methodologies, motivations, domain examples, benefits, challenges, and future research agenda under this paradigm.