mlsanityData to 7 Oct 2026

The Duet of Representations and How Explanations Exacerbate It

arXiv 2402.08379 ↗First posted 13 Feb 2024cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

An algorithm effects a causal representation of relations between features and labels in the human's perception. Such a representation might conflict with the human's prior belief. Explanations can direct the human's attention to the conflicting feature and away from other relevant features. This leads to causal overattribution and may adversely affect the human's information processing. In a field experiment we implemented an XGBoost-trained model as a decision-making aid for counselors at a public employment service to predict candidates' risk of long-term unemployment. The treatment group of counselors was also provided with SHAP. The results show that the quality of the human's decision-making is worse when a feature on which the human holds a conflicting prior belief is displayed as part of the explanation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 37 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

11 of 37 references.

References · 11

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  4. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 166
  5. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  6. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  7. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  8. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  9. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  10. 2021Human-AI Collaboration with Bandit Feedbackcited by 36
  11. 2022Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-makingcited by 4

Built on by

Not cited yet.