# Optimising Human-AI Collaboration by Learning Convincing Explanations

arXiv: https://arxiv.org/abs/2311.07426 · HTML: https://mlsanity.com/paper/2311.07426/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Cascading Bandits: Learning to Rank in the Cascade Model](https://mlsanity.com/paper/1502.02763/) (2015)
- [Scalable Bayesian Inverse Reinforcement Learning](https://mlsanity.com/paper/2102.06483/) (2021)
- [MNL-Bandit: A Dynamic Learning Approach to Assortment Selection](https://mlsanity.com/paper/1706.03880/) (2017)
- [Explaining Latent Representations with a Corpus of Examples](https://mlsanity.com/paper/2110.15355/) (2021)
- [Estimating and Penalizing Induced Preference Shifts in Recommender Systems](https://mlsanity.com/paper/2204.11966/) (2022)
- [Uncalibrated Models Can Improve Human-AI Collaboration](https://mlsanity.com/paper/2202.05983/) (2022)
- [Interpreting Neural Networks With Nearest Neighbors](https://mlsanity.com/paper/1809.02847/) (2018)
- [POETREE: Interpretable Policy Learning with Adaptive Decision Trees](https://mlsanity.com/paper/2203.08057/) (2022)
- [Inverse Contextual Bandits: Learning How Behavior Evolves over Time](https://mlsanity.com/paper/2107.06317/) (2021)
- [What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems](https://mlsanity.com/paper/1811.10799/) (2018)
- [The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation](https://mlsanity.com/paper/2106.04240/) (2021)
- [Inverse Decision Modeling: Learning Interpretable Representations of Behavior](https://mlsanity.com/paper/2310.18591/) (2023)
- [Sequential Explanations with Mental Model-Based Policies](https://mlsanity.com/paper/2007.09028/) (2020)
- [Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies](https://mlsanity.com/paper/2203.07338/) (2022)
- [Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes](https://mlsanity.com/paper/2211.06138/) (2022)

## Built on by (most cited first, 1 of 1)

- [Dense Reward for Free in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2402.00782/) (2024)

## Abstract (arXiv)

Machine learning models are being increasingly deployed to take, or assist in taking, complicated and high-impact decisions, from quasi-autonomous vehicles to clinical decision support systems. This poses challenges, particularly when models have hard-to-detect failure modes and are able to take actions without oversight. In order to handle this challenge, we propose a method for a collaborative system that remains safe by having a human ultimately making decisions, while giving the model the best opportunity to convince and debate them with interpretable explanations. However, the most helpful explanation varies among individuals and may be inconsistent across stated preferences. To this end we develop an algorithm, Ardent, to efficiently learn a ranking through interaction and best assist humans complete a task. By utilising a collaborative approach, we can ensure safety and improve performance while addressing transparency and accountability concerns. Ardent enables efficient and effective decision-making by adapting to individual preferences for explanations, which we validate through extensive simulations alongside a user study involving a challenging image classification task, demonstrating consistent improvement over competing systems.