The Neglected Baseline in Model Interpretation

• URL: http://arxiv.org/abs/2605.22417v3
• Date: Tue, 26 May 2026 15:47:46 GMT
• Title: The Neglected Baseline in Model Interpretation
• Abstract summary: We reformulate the task of model interpretation and the interpretation principles to demonstrate the importance of the baseline.<n>We further unify gradient-based methods, Integrated Gradients (IG) methods, and Taylor expansion, clarifying the connections among them.<n>On this basis, we analyze the flaws and errors in related model interpretation methods.
• Score: 2.1760536522571807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect interpretation. In this paper, we reformulate the task of model interpretation and the interpretation principles for model interpretation results to demonstrate the importance of the baseline. We further unify gradient-based methods, Integrated Gradients (IG) methods, and Taylor expansion, clarifying the connections among them and explicitly identifying the baseline for each method. On this basis, we analyze the flaws and errors in related model interpretation methods (IG, LayerCAM, ODAM, Difference Map). We advocate evaluating the quality of model interpretation results precisely through the attribution error between the attribution result and the attribution target, rather than adopting flawed evaluation methods, such as those based on marginal-effect or the assumption of perfect model performance. We revise IG and develope a model interpretation method with a clear and reasonable baseline, achieving better results. Our method supports model interpretation based on features from any layer. Interpretation based on features from different layers are all reasonable, and the differences among these results reflect varying degrees of feature extraction at different feature extraction stages.

Related papers

• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check [60.77691669644931]
  We propose Functional Alignment for Distributional Equivalence (FADE), a novel metric that measures distributional similarity between unlearned and reference models.<n>We show that FADE captures functional alignment across the entire output distribution, providing a principled assessment of genuine unlearning.<n>These findings expose fundamental gaps in current evaluation practices and demonstrate that FADE provides a more robust foundation for developing and assessing truly effective unlearning methods.
  arXiv  Detail & Related papers  (2025-10-14T20:50:30Z)
• Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks [9.390951257874187]
  We introduce a standardized protocol to quantify informativeness, equivariance, invariance, and disentanglement of factors of variation in model representations.<n>We find that representations from models with similar downstream performance can behave substantially differently with regard to these attributes.
  arXiv  Detail & Related papers  (2025-05-09T17:58:52Z)
• Towards credible visual model interpretation with path attribution [24.86176236641865]
  path attribution framework stands out among the post-hoc model interpretation tools due to its axiomatic nature. Recent developments show that this framework can still suffer from counter-intuitive results. We devise a scheme to preclude the conditions in which visual model interpretation can invalidate the axiomatic properties of path attribution.
  arXiv  Detail & Related papers  (2023-05-23T06:23:08Z)
• 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)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)
• Learning Causal Semantic Representation for Out-of-Distribution Prediction [125.38836464226092]
  We propose a Causal Semantic Generative model (CSG) based on a causal reasoning so that the two factors are modeled separately. We show that CSG can identify the semantic factor by fitting training data, and this semantic-identification guarantees the boundedness of OOD generalization error.
  arXiv  Detail & Related papers  (2020-11-03T13:16:05Z)
• Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
  This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets. Part of the challenge of learning robust models lies in the influence of unobserved confounders. We demonstrate the empirical performance of our approach on healthcare data from different modalities.
  arXiv  Detail & Related papers  (2020-07-21T08:18:06Z)
• General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models [1.025459377812322]
  We highlight many general pitfalls of machine learning model interpretation, such as using interpretation techniques in the wrong context. We focus on pitfalls for global methods that describe the average model behavior, but many pitfalls also apply to local methods that explain individual predictions.
  arXiv  Detail & Related papers  (2020-07-08T14:02:56Z)
• 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.