Can AI Mitigate Human Perceptual Biases? A Pilot Study

• URL: http://arxiv.org/abs/2311.00706v1
• Date: Tue, 10 Oct 2023 21:35:15 GMT
• Title: Can AI Mitigate Human Perceptual Biases? A Pilot Study
• Abstract summary: We present results from a pilot experiment to measure if machine recommendations can debias human biases in visualization tasks. We specifically studied the pull-down'' effect, for the task of estimating the ensemble average of data points in line charts. Our pilot study showed that participants were faster with AI assistance in ensemble tasks, compared to the baseline without AI assistance.
• Score: 3.2997705040068253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Cognitive offloading and the speedup illusion in human-AI interaction [39.088619511248986]
  Large language models (LLMs) have the potential to boost human productivity by speeding up task completion.<n>We conducted a large-scale behavioral study to characterize mismatches between expectations and reality.<n>We identify a speedup illusion where people have accurate forecasts of independent completion times but significantly underestimate AI-assisted times.
  arXiv  Detail & Related papers  (2026-05-22T02:53:12Z)
• AI Assistance Reduces Persistence and Hurts Independent Performance [1.3667120179358196]
  We provide evidence for two key consequences of AI assistance: reduced persistence and impairment of unassisted performance.<n>We find that although AI assistance improves performance in the short-term, people perform significantly worse without AI and are more likely to give up.<n>These results suggest the need for AI model development to prioritize long-term competence alongside immediate task completion.
  arXiv  Detail & Related papers  (2026-04-06T14:43:48Z)
• Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The Public [46.86429592892395]
  explainable AI (XAI) addresses this by providing AI decision-making insight.<n>We present results from two large-scale experiments combining a fairness-based diagnosis AI model and different XAI explanations.
  arXiv  Detail & Related papers  (2025-12-14T00:06:06Z)
• From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions [8.60890432697274]
  We designed a helpful AI "Peer" to help students correct fundamental physics misconceptions related to Newtonian mechanic concepts. In a randomized controlled trial with 165 students, those who engaged in targeted dialogue with the AI Peer achieved post-test scores that were, on average, 10.5 percentage points higher.
  arXiv  Detail & Related papers  (2025-04-01T04:09:13Z)
• Observation Interference in Partially Observable Assistance Games [34.53170543153206]
  We study a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. We show that sometimes an optimal assistant must take observation-interfering actions, even when the human is playing optimally. We show that if the human acts according to the Boltzmann model of irrationality, this can create an incentive for the assistant to interfere with observations.
  arXiv  Detail & Related papers  (2024-12-23T18:53:33Z)
• Raising the Stakes: Performance Pressure Improves AI-Assisted Decision Making [57.53469908423318]
  We show the effects of performance pressure on AI advice reliance when laypeople complete a common AI-assisted task. We find that when the stakes are high, people use AI advice more appropriately than when stakes are lower, regardless of the presence of an AI explanation.
  arXiv  Detail & Related papers  (2024-10-21T22:39:52Z)
• Comparing Zealous and Restrained AI Recommendations in a Real-World Human-AI Collaboration Task [11.040918613968854]
  We argue that careful exploitation of the tradeoff between precision and recall can significantly improve team performance. We analyze the performance of 78 professional annotators working with a) no AI assistance, b) a high-precision "restrained" AI, and c) a high-recall "zealous" AI in over 3,466 person-hours of annotation work.
  arXiv  Detail & Related papers  (2024-10-06T23:19:19Z)
• Confident Teacher, Confident Student? A Novel User Study Design for Investigating the Didactic Potential of Explanations and their Impact on Uncertainty [1.0855602842179624]
  We investigate the impact of explanations on human performance on a challenging visual task using Explainable Artificial Intelligence (XAI) We find that users become more accurate in their annotations and demonstrate less uncertainty with AI assistance. We also find negative effects of explanations: users tend to replicate the model's predictions more often when shown explanations.
  arXiv  Detail & Related papers  (2024-09-10T12:59:50Z)
• HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World [48.90399899928823]
  This work is part of a broader research effort to develop intelligent agents that can interactively guide humans through performing tasks in the physical world. We introduce HoloAssist, a large-scale egocentric human interaction dataset. We present key insights into how human assistants correct mistakes, intervene in the task completion procedure, and ground their instructions to the environment.
  arXiv  Detail & Related papers  (2023-09-29T07:17:43Z)
• Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making [5.381004207943597]
  We conducted an experiment with seven therapists and ten laypersons on the task of assessing post-stroke survivors' quality of motion. We analyzed their performance, agreement level on the task, and reliance on AI without and with two types of AI explanations. Our work discusses the potential of counterfactual explanations to better estimate the accuracy of an AI model and reduce over-reliance on wrong' AI outputs.
  arXiv  Detail & Related papers  (2023-08-08T16:23:46Z)
• Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
  We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
  arXiv  Detail & Related papers  (2023-04-16T11:22:59Z)
• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias [57.87117733071416]
  We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases. A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
  arXiv  Detail & Related papers  (2022-08-10T03:41:48Z)
• Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment [52.07473934146584]
  We guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level.
  arXiv  Detail & Related papers  (2022-08-04T23:53:51Z)
• Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making [19.157591744997355]
  We argue that the typical experimental setup limits the potential of human-AI teams. We develop novel interfaces to support interactive explanations so that humans can actively engage with AI assistance.
  arXiv  Detail & Related papers  (2021-01-13T19:01:32Z)
• Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance [44.730580857733]
  Prior studies observed improvements from explanations only when the AI, alone, outperformed both the human and the best team. We conduct mixed-method user studies on three datasets, where an AI with accuracy comparable to humans helps participants solve a task. We find explanations increase the chance that humans will accept the AI's recommendation, regardless of its correctness.
  arXiv  Detail & Related papers  (2020-06-26T03:34:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.