For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI

• URL: http://arxiv.org/abs/2306.07637v1
• Date: Tue, 13 Jun 2023 09:16:38 GMT
• Title: For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI
• Authors: Ulrike Kuhl and Andr\'e Artelt and Barbara Hammer
• Abstract summary: Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI) CFEs describe a scenario that is better than the factual state (upward CFE), or a scenario that is worse than the factual state (downward CFE) This study compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system.
• Score: 6.883906273999368
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model's output. A CFE can either describe a scenario that is better than the factual state (upward CFE), or a scenario that is worse than the factual state (downward CFE). However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear. The current user study (N=161) compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system based on model predictions and CFEs. Results suggest that upward CFEs provide a significant performance advantage over other forms of counterfactual feedback. Moreover, the study highlights potential benefits of mixed CFEs improving user performance compared to downward CFEs or no explanations. In line with the performance results, users' explicit knowledge of the system is statistically higher after receiving upward CFEs compared to downward comparisons. These findings imply that the alignment between explanation and task at hand, the so-called regulatory fit, may play a crucial role in determining the effectiveness of model explanations, informing future research directions in xAI. To ensure reproducible research, the entire code, underlying models and user data of this study is openly available: https://github.com/ukuhl/DirectionalAlienZoo

Related papers

• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance [61.06245197347139]
  We propose a novel approach to explain the behavior of a black-box model under feature shifts. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation.
  arXiv  Detail & Related papers  (2024-08-24T18:28:19Z)
• Value of Information and Reward Specification in Active Inference and POMDPs [7.120454740315046]
  Expected free energy (EFE) is a central quantity in active inference. We show that EFE approximates the Bayes optimal RL policy via information value.
  arXiv  Detail & Related papers  (2024-08-13T00:32:05Z)
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations [56.941276017696076]
  We propose a conceptually simple yet effective solution named Counterfactual Explanations with Minimal Satisfiable Perturbations (CEMSP) CEMSP constrains changing values of abnormal features with the help of their semantically meaningful normal ranges. Compared to existing methods, we conduct comprehensive experiments on both synthetic and real-world datasets to demonstrate that our method provides more robust explanations while preserving flexibility.
  arXiv  Detail & Related papers  (2023-09-09T04:05:56Z)
• Prediction-Oriented Bayesian Active Learning [51.426960808684655]
  Expected predictive information gain (EPIG) is an acquisition function that measures information gain in the space of predictions rather than parameters. EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models.
  arXiv  Detail & Related papers  (2023-04-17T10:59:57Z)
• Unlearning Protected User Attributes in Recommendations with Adversarial Training [10.268369743620159]
  Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users. These encoded biases can influence the decision of a recommendation system towards further separation of the contents provided to various demographic subgroups. In this work, we investigate the possibility and challenges of removing specific protected information of users from the learned interaction representations of a RS algorithm.
  arXiv  Detail & Related papers  (2022-06-09T13:36:28Z)
• Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting [6.883906273999368]
  Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. Recent innovations introduce the notion of computational plausibility for automatically generated CFEs. We evaluate objective and subjective usability of computationally plausible CFEs in an iterative learning design targeting novice users.
  arXiv  Detail & Related papers  (2022-05-11T14:07:57Z)
• Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learning [6.883906273999368]
  Counterfactual explanations (CFEs) have gained traction as a psychologically grounded approach to generate post-hoc explanations. We introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework. As a proof of concept, we demonstrate the practical efficacy and feasibility of this approach in a user study.
  arXiv  Detail & Related papers  (2022-05-06T17:57:05Z)
• Enhancing User' s Income Estimation with Super-App Alternative Data [59.60094442546867]
  It compares the performance of these alternative data sources with the performance of industry-accepted bureau income estimators. Ultimately, this paper shows the incentive for financial institutions to seek to incorporate alternative data into constructing their risk profiles.
  arXiv  Detail & Related papers  (2021-04-12T21:34:44Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)

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.