mlsanityData to 7 Oct 2026

One Explanation Does Not Fit XIL

arXiv 2304.07136 ↗First posted 14 Apr 2023cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the explanatory interactive machine learning (XIL) framework has been proposed to revise a model by employing user feedback on a model's explanation. This work sheds light on the explanations used within this framework. In particular, we investigate simultaneous model revision through multiple explanation methods. To this end, we identified that textitone explanation does not fit XIL and propose considering multiple ones when revising models via XIL.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

19 of 23 references.

References · 19

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2018Sanity Checks for Saliency Mapscited by 1,149
  8. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  9. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  10. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  11. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  12. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 149
7 more
  1. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  2. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 141
  3. 2019Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Groundedcited by 127
  4. 2020One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparencycited by 64
  5. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  6. 2016Interpretation of Prediction Models Using the Input Gradientcited by 24
  7. 2016Enlightening Deep Neural Networks with Knowledge of Confounding Factorscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Right on Time: Revising Time Series Models by Constraining their Explanationscited by 7
  2. 2024Interpretable end-to-end Neurosymbolic Reinforcement Learning agentscited by 4