Fixing confirmation bias in feature attribution methods via semantic match

• URL: http://arxiv.org/abs/2307.00897v3
• Date: Mon, 26 Feb 2024 10:34:10 GMT
• Title: Fixing confirmation bias in feature attribution methods via semantic match
• Authors: Giovanni Cin\`a, Daniel Fernandez-Llaneza, Ludovico Deponte, Nishant Mishra, Tabea E. R\"ober, Sandro Pezzelle, Iacer Calixto, Rob Goedhart, \c{S}. \.Ilker Birbil
• Abstract summary: We argue that a structured approach is required to test whether our hypotheses on the model are confirmed by the feature attributions. This is what we call the "semantic match" between human concepts and (sub-symbolic) explanations.
• Score: 4.733072355085082
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Feature attribution methods have become a staple method to disentangle the complex behavior of black box models. Despite their success, some scholars have argued that such methods suffer from a serious flaw: they do not allow a reliable interpretation in terms of human concepts. Simply put, visualizing an array of feature contributions is not enough for humans to conclude something about a model's internal representations, and confirmation bias can trick users into false beliefs about model behavior. We argue that a structured approach is required to test whether our hypotheses on the model are confirmed by the feature attributions. This is what we call the "semantic match" between human concepts and (sub-symbolic) explanations. Building on the conceptual framework put forward in Cin\`a et al. [2023], we propose a structured approach to evaluate semantic match in practice. We showcase the procedure in a suite of experiments spanning tabular and image data, and show how the assessment of semantic match can give insight into both desirable (e.g., focusing on an object relevant for prediction) and undesirable model behaviors (e.g., focusing on a spurious correlation). We couple our experimental results with an analysis on the metrics to measure semantic match, and argue that this approach constitutes the first step towards resolving the issue of confirmation bias in XAI.

Related papers

• Counterfactual Generation from Language Models [64.55296662926919]
  We show that counterfactual reasoning is conceptually distinct from interventions. We propose a framework for generating true string counterfactuals. Our experiments demonstrate that the approach produces meaningful counterfactuals.
  arXiv  Detail & Related papers  (2024-11-11T17:57:30Z)
• Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance [72.50214227616728]
  Interpretability methods are valuable only if their explanations faithfully describe the explained model. We consider neural networks whose predictions are invariant under a specific symmetry group.
  arXiv  Detail & Related papers  (2023-04-13T17:59:03Z)
• ContraFeat: Contrasting Deep Features for Semantic Discovery [102.4163768995288]
  StyleGAN has shown strong potential for disentangled semantic control. Existing semantic discovery methods on StyleGAN rely on manual selection of modified latent layers to obtain satisfactory manipulation results. We propose a model that automates this process and achieves state-of-the-art semantic discovery performance.
  arXiv  Detail & Related papers  (2022-12-14T15:22:13Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• Counterfactual Evaluation for Explainable AI [21.055319253405603]
  We propose a new methodology to evaluate the faithfulness of explanations from the textitcounterfactual reasoning perspective. We introduce two algorithms to find the proper counterfactuals in both discrete and continuous scenarios and then use the acquired counterfactuals to measure faithfulness.
  arXiv  Detail & Related papers  (2021-09-05T01:38:49Z)
• On the Lack of Robust Interpretability of Neural Text Classifiers [14.685352584216757]
  We assess the robustness of interpretations of neural text classifiers based on pretrained Transformer encoders. Both tests show surprising deviations from expected behavior, raising questions about the extent of insights that practitioners may draw from interpretations.
  arXiv  Detail & Related papers  (2021-06-08T18:31:02Z)
• Robust Semantic Interpretability: Revisiting Concept Activation Vectors [0.0]
  Interpretability methods for image classification attempt to expose whether the model is systematically biased or attending to the same cues as a human would. Our proposed Robust Concept Activation Vectors (RCAV) quantifies the effects of semantic concepts on individual model predictions and on model behavior as a whole.
  arXiv  Detail & Related papers  (2021-04-06T20:14:59Z)
• Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability [44.60486560836836]
  Any prediction from a model is made by a combination of learning history and test stimuli. Existing methods to interpret a model's predictions are only able to capture a single aspect of either test stimuli or learning history. We propose an efficient and differentiable approach to make it feasible to interpret a model's prediction by jointly examining training history and test stimuli.
  arXiv  Detail & Related papers  (2020-10-14T10:45:01Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)

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.