mlsanityData to 7 Oct 2026

Let the CAT out of the bag: Contrastive Attributed explanations for Text

arXiv 2109.07983 ↗First posted 16 Sep 2021cs.CL cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explanations for Text (CAT) which provides contrastive explanations for natural language text data with a novel twist as we build and exploit attribute classifiers leading to more semantically meaningful explanations. To ensure that our contrastive generated text has the fewest possible edits with respect to the original text, while also being fluent and close to a human generated contrastive, we resort to a minimal perturbation approach regularized using a BERT language model and attribute classifiers trained on available attributes. We show through qualitative examples and a user study that our method not only conveys more insight because of these attributes, but also leads to better quality (contrastive) text. Quantitatively, we show that our method outperforms other state-of-the-art methods across four data sets on four benchmark metrics.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

39 of 52 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  12. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
27 more
  1. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  2. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  3. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  4. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  5. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 414
  6. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  7. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  8. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  9. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  10. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  11. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 219
  12. 2019Explainable Machine Learning in Deploymentcited by 210
  13. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  14. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  15. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  16. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  17. 2018Pathologies of Neural Models Make Interpretations Difficultcited by 140
  18. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 105
  19. 2020Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Textcited by 75
  20. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  21. 2018Hierarchical interpretations for neural network predictionscited by 66
  22. 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
  23. 2021An Investigation of the (In)effectiveness of Counterfactually Augmented Datacited by 42
  24. 2019Model Agnostic Contrastive Explanations for Structured Datacited by 41
  25. 2020Model Agnostic Multilevel Explanationscited by 24
  26. 2019Leveraging Latent Features for Local Explanationscited by 21
  27. 2018Interpreting Neural Networks With Nearest Neighborscited by 18

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 1.

9 papers.

  1. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  2. 2024A Survey on Natural Language Counterfactual Generationcited by 21
  3. 2023EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verificationcited by 9
  4. 2023Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differencescited by 8
  5. 2023Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editorscited by 6
  6. 2025The Unheard Alternative: Contrastive Explanations for Speech-to-Text Modelscited by 3
  7. 2022A General Search-based Framework for Generating Textual Counterfactual Explanationscited by 2
  8. 2022Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanationscited by 0
  9. 2024CELL your Model: Contrastive Explanations for Large Language Modelscited by 0