mlsanityData to 14 Oct 2026

TIGTEC : Token Importance Guided TExt Counterfactuals

arXiv 2304.12425 ↗First posted 24 Apr 2023cs.LG cs.CL stat.MEcited by 8

Not on the map. Why?

Abstract (arXiv)

Counterfactual examples explain a prediction by highlighting changes of instance that flip the outcome of a classifier. This paper proposes TIGTEC, an efficient and modular method for generating sparse, plausible and diverse counterfactual explanations for textual data. TIGTEC is a text editing heuristic that targets and modifies words with high contribution using local feature importance. A new attention-based local feature importance is proposed. Counterfactual candidates are generated and assessed with a cost function integrating semantic distance, while the solution space is efficiently explored in a beam search fashion. The conducted experiments show the relevance of TIGTEC in terms of success rate, sparsity, diversity and plausibility. This method can be used in both model-specific or model-agnostic way, which makes it very convenient for generating counterfactual explanations.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 24 Apr 2023.

Builds on

23 of 31 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  9. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  10. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  11. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  12. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
11 more
  1. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  2. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  3. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 222
  4. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  5. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 106
  6. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  7. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 75
  8. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  9. 2021Text Counterfactuals via Latent Optimization and Shapley-Guided Searchcited by 16
  10. 2023Evaluating self-attention interpretability through human-grounded experimental protocolcited by 5
  11. 2022Plug and Play Counterfactual Text Generation for Model Robustnesscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 3.

8 papers.

  1. 2024Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanationscited by 8
  2. 2025FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generationcited by 6
  3. 2024Mitigating Text Toxicity with Counterfactual Generationcited by 2
  4. 2025CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triplescited by 1
  5. 2026Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generationcited by 1
  6. 2026iFlip: Iterative Feedback-driven Counterfactual Example Refinementcited by 1
  7. 2026DRIV-EX: Counterfactual Explanations for Driving LLMscited by 1
  8. 2025Conceptual Contrastive Edits in Textual and Vision-Language Retrievalcited by 0