mlsanityData to 14 Oct 2026

Towards Benchmarking the Utility of Explanations for Model Debugging

arXiv 2105.04505 ↗First posted 10 May 2021cs.AI cs.HC cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 15 of its 18 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

15 of 18 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  6. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  8. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  9. 2019Probing Neural Network Comprehension of Natural Language Argumentscited by 214
  10. 2019Explainable Machine Learning in Deploymentcited by 211
  11. 2020Debugging Tests for Model Explanationscited by 147
  12. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
3 more
  1. 2019Incorporating Priors with Feature Attribution on Text Classificationcited by 68
  2. 2017The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrantscited by 56
  3. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 2.

10 papers.

  1. 2021"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classificationcited by 66
  2. 2023Post Hoc Explanations of Language Models Can Improve Language Modelscited by 50
  3. 2022Evaluation Gaps in Machine Learning Practicecited by 49
  4. 2023Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationalescited by 37
  5. 2022XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Modelscited by 8
  6. 2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
  7. 2023May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainabilitycited by 5
  8. 2024Explainable Interface for Human-Autonomy Teaming: A Surveycited by 2
  9. 2022SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactualscited by 1
  10. 2024DISCO: DISCovering Overfittings as Causal Rules for Text Classification Modelscited by 0