# Can AI Mitigate Human Perceptual Biases? A Pilot Study

arXiv: https://arxiv.org/abs/2311.00706 · HTML: https://mlsanity.com/paper/2311.00706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 10 of 10)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Counterfactual Explanations Can Be Manipulated](https://mlsanity.com/paper/2106.02666/) (2021)
- [Rethinking Explainability as a Dialogue: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01875/) (2022)
- [Assessing the Impact of Automated Suggestions on Decision Making: Domain Experts Mediate Model Errors but Take Less Initiative](https://mlsanity.com/paper/2103.04725/) (2021)
- [The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning](https://mlsanity.com/paper/2203.06498/) (2022)
- [The human-AI relationship in decision-making: AI explanation to support people on justifying their decisions](https://mlsanity.com/paper/2102.05460/) (2021)
- [How to evaluate data visualizations across different levels of understanding](https://mlsanity.com/paper/2009.01747/) (2020)
- [Biased Average Position Estimates in Line and Bar Graphs: Underestimation, Overestimation, and Perceptual Pull](https://mlsanity.com/paper/1908.00073/) (2019)
- [Visual Validation versus Visual Estimation: A Study on the Average Value in Scatterplots](https://mlsanity.com/paper/2307.09330/) (2023)
- [Measuring the Effects of Scalar and Spherical Colormaps on Ensembles of DMRI Tubes](https://mlsanity.com/paper/1810.07882/) (2018)

## Abstract (arXiv)

We present results from a pilot experiment to measure if machine recommendations can debias human perceptual biases in visualization tasks. We specifically studied the ``pull-down'' effect, i.e., people underestimate the average position of lines, for the task of estimating the ensemble average of data points in line charts. These line charts can show for example temperature or precipitation in 12 months. Six participants estimated ensemble averages with or without an AI assistant. The assistant, when available, responded at three different speeds to assemble the conditions of a human collaborator who may delay his or her responses. Our pilot study showed that participants were faster with AI assistance in ensemble tasks, compared to the baseline without AI assistance. Although ``pull-down'' biases were reduced, the effect of AI assistance was not statistically significant. Also, delaying AI responses had no significant impact on human decision accuracy. We discuss the implications of these preliminary results for subsequent studies.