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



  • Yada Zhu
  • Xiaodong Cui
  • Fan Zhang
  • Guangnan Ye
  • Ziming Huang
  • Wei Zhang

Published on


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 retraining 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.

Please cite our work using the BibTeX below.

    title = "On Sample Based Explanation Methods for {NLP}: Faithfulness, Efficiency and Semantic Evaluation",
    author = "Zhang, Wei  and
      Huang, Ziming  and
      Zhu, Yada  and
      Ye, Guangnan  and
      Cui, Xiaodong  and
      Zhang, Fan",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "",
    doi = "10.18653/v1/2021.acl-long.419",
    pages = "5399--5411",
Close Modal