mlsanityData to 14 Oct 2026

Human-grounded Evaluations of Explanation Methods for Text Classification

arXiv 1908.11355 ↗First posted 29 Aug 2019cs.CL cs.AI cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Due to the black-box nature of deep learning models, methods for explaining the models' results are crucial to gain trust from humans and support collaboration between AIs and humans. In this paper, we consider several model-agnostic and model-specific explanation methods for CNNs for text classification and conduct three human-grounded evaluations, focusing on different purposes of explanations: (1) revealing model behavior, (2) justifying model predictions, and (3) helping humans investigate uncertain predictions. The results highlight dissimilar qualities of the various explanation methods we consider and show the degree to which these methods could serve for each purpose.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 7; 2023: 3; 2024: 3; 2025: 1.

28 papers.

Sort:

  1. 2021A Survey on Automated Fact-Checkingcited by 378
  2. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  3. 2021SelfExplain: A Self-Explaining Architecture for Neural Text Classifierscited by 44
  4. 2021Explainable AI: current status and future directionscited by 33
  5. 2021Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retrainingcited by 31
  6. 2021Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanationscited by 26
  7. 2022ferret: a Framework for Benchmarking Explainers on Transformerscited by 26
  8. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  9. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
  10. 2022Towards Explainable Evaluation Metrics for Natural Language Generationcited by 15
  11. 2021On the Interaction of Belief Bias and Explanationscited by 13
  12. 2021Thermostat: A Large Collection of NLP Model Explanations and Analysis Toolscited by 11
16 more
  1. 2023Why is plausibility surprisingly problematic as an XAI criterion?cited by 9
  2. 2022Are Shortest Rationales the Best Explanations for Human Understanding?cited by 8
  3. 2022An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classificationcited by 6
  4. 2021XPROAX-Local explanations for text classification with progressive neighborhood approximationcited by 5
  5. 2024SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approachcited by 4
  6. 2022Towards Human-Centred Explainability Benchmarks For Text Classificationcited by 2
  7. 2024A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learningcited by 2
  8. 2021Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarmscited by 1
  9. 2021Combining Transformers with Natural Language Explanationscited by 1
  10. 2022Argumentative Explanations for Pattern-Based Text Classifierscited by 1
  11. 2023Explaining text classifiers through progressive neighborhood approximation with realistic samplescited by 1
  12. 2025Can LLM Assist in the Evaluation of the Quality of Machine Learning Explanations?cited by 1
  13. 2021A Symmetric Loss Perspective of Reliable Machine Learningcited by 0
  14. 2021Interpretable Feature Learning Framework for Smoking Behavior Detectioncited by 0
  15. 2023Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspectivecited by 0
  16. 2024A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweetscited by 0