mlsanityData to 7 Oct 2026

On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation

arXiv 2106.04753 ↗First posted 9 Jun 2021cs.CL cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness. In this work, for the first time, we can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit. On top of this, we implement a hessian-free method with a model faithfulness guarantee. Finally, to compare our method with the others, we propose a semantic-based evaluation metric that can better align with humans' judgment of explanations than the widely adopted diagnostic or re-training measures. The empirical results on multiple real data sets demonstrate the proposed method's superior performance to popular explanation techniques such as Influence Function or TracIn on semantic evaluation.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

31 of 42 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  8. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  9. 2019Attention is not Explanationcited by 916
  10. 2019Attention is not not Explanationcited by 629
  11. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  12. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
19 more
  1. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  2. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  3. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  4. 2019Is Attention Interpretable?cited by 387
  5. 2020Influence Functions in Deep Learning Are Fragilecited by 247
  6. 2016Understanding Neural Networks through Representation Erasurecited by 223
  7. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
  8. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 146
  9. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  10. 2020Evaluating Explanations: How much do explanations from the teacher aid students?cited by 94
  11. 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
  12. 2020Generative Data Augmentation for Commonsense Reasoningcited by 49
  13. 2020Interpretation of NLP models through input marginalizationcited by 43
  14. 2019Variational Pretraining for Semi-supervised Text Classificationcited by 41
  15. 2016SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoodscited by 32
  16. 2020Evaluating Attribution Methods using White-Box LSTMscited by 8
  17. 2020Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretabilitycited by 7
  18. 2020Evaluation of Similarity-based Explanationscited by 2
  19. 2016Tricks from Deep Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 4; 2024: 0; 2025: 0; 2026: 1.

12 papers.

  1. 2022Towards Tracing Factual Knowledge in Language Models Back to the Training Datacited by 21
  2. 2022Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Treescited by 16
  3. 2022Improved Target-specific Stance Detection on Social Media Platforms by Delving into Conversation Threadscited by 16
  4. 2022Diagnosing AI Explanation Methods with Folk Concepts of Behaviorcited by 15
  5. 2022Influence Functions for Sequence Tagging Modelscited by 9
  6. 2021AI Explainability 360: Impact and Designcited by 8
  7. 2023Users are the North Star for AI Transparencycited by 5
  8. 2023On Pitfalls of textitRemOve-And-Retrain: Data Processing Inequality Perspectivecited by 2
  9. 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Modelscited by 1
  10. 2023Wrapper Boxes: Faithful Attribution of Model Predictions to Training Datacited by 1
  11. 2026Compact Example-Based Explanations for Language Modelscited by 1
  12. 2021Explaining Deep Learning Representations by Tracing the Training Processcited by 0