In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making

• URL: http://arxiv.org/abs/2305.07722v4
• Date: Thu, 1 Feb 2024 23:05:51 GMT
• Title: In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making
• Authors: Raymond Fok, Daniel S. Weld
• Abstract summary: We argue explanations are only useful to the extent that they allow a human decision maker to verify the correctness of an AI's prediction. We also compare the objective of complementary performance with that of appropriate reliance, decomposing the latter into the notions of outcome-graded and strategy-graded reliance.
• Score: 25.18203172421461
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The current literature on AI-advised decision making -- involving explainable AI systems advising human decision makers -- presents a series of inconclusive and confounding results. To synthesize these findings, we propose a simple theory that elucidates the frequent failure of AI explanations to engender appropriate reliance and complementary decision making performance. We argue explanations are only useful to the extent that they allow a human decision maker to verify the correctness of an AI's prediction, in contrast to other desiderata, e.g., interpretability or spelling out the AI's reasoning process. Prior studies find in many decision making contexts AI explanations do not facilitate such verification. Moreover, most tasks fundamentally do not allow easy verification, regardless of explanation method, limiting the potential benefit of any type of explanation. We also compare the objective of complementary performance with that of appropriate reliance, decomposing the latter into the notions of outcome-graded and strategy-graded reliance.

Related papers

• Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
  We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks. We show that the learned AI control system demonstrates robustness against adversarial tampering. In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
  arXiv  Detail & Related papers  (2024-07-03T15:38:57Z)
• Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making [47.33241893184721]
  In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. We propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates.
  arXiv  Detail & Related papers  (2024-03-25T14:34:06Z)
• A Decision Theoretic Framework for Measuring AI Reliance [23.353778024330165]
  Humans frequently make decisions with the aid of artificially intelligent (AI) systems. Researchers have identified ensuring that a human has appropriate reliance on an AI as a critical component of achieving complementary performance. We propose a formal definition of reliance, based on statistical decision theory, which separates the concepts of reliance as the probability the decision-maker follows the AI's recommendation.
  arXiv  Detail & Related papers  (2024-01-27T09:13:09Z)
• On the Interdependence of Reliance Behavior and Accuracy in AI-Assisted Decision-Making [0.0]
  We analyze the interdependence between reliance behavior and accuracy in AI-assisted decision-making. We propose a visual framework to make this interdependence more tangible.
  arXiv  Detail & Related papers  (2023-04-18T08:08:05Z)
• Selective Explanations: Leveraging Human Input to Align Explainable AI [40.33998268146951]
  We propose a general framework for generating selective explanations by leveraging human input on a small sample. As a showcase, we use a decision-support task to explore selective explanations based on what the decision-maker would consider relevant to the decision task. Our experiments demonstrate the promise of selective explanations in reducing over-reliance on AI.
  arXiv  Detail & Related papers  (2023-01-23T19:00:02Z)
• Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations [44.01143305912054]
  We study how decision-makers' intuition affects their use of AI predictions and explanations. Our results identify three types of intuition involved in reasoning about AI predictions and explanations. We use these pathways to explain why feature-based explanations did not improve participants' decision outcomes and increased their overreliance on AI.
  arXiv  Detail & Related papers  (2023-01-18T01:33:50Z)
• On the Relationship Between Explanations, Fairness Perceptions, and Decisions [2.5372245630249632]
  It is known that recommendations of AI-based systems can be incorrect or unfair. It is often proposed that a human be the final decision-maker. Prior work has argued that explanations are an essential pathway to help human decision-makers enhance decision quality.
  arXiv  Detail & Related papers  (2022-04-27T19:33:36Z)
• The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
  We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
  arXiv  Detail & Related papers  (2021-07-28T17:32:04Z)
• Decision Rule Elicitation for Domain Adaptation [93.02675868486932]
  Human-in-the-loop machine learning is widely used in artificial intelligence (AI) to elicit labels from experts. In this work, we allow experts to additionally produce decision rules describing their decision-making. We show that decision rule elicitation improves domain adaptation of the algorithm and helps to propagate expert's knowledge to the AI model.
  arXiv  Detail & Related papers  (2021-02-23T08:07:22Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

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.