mlsanityData to 14 Oct 2026

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

arXiv 2210.16978 ↗First posted 30 Oct 2022cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model. While existing model debugging methods have shown promise, their prototype-level implementations provide limited practical utility. Thus, we propose XMD: the first open-source, end-to-end framework for explanation-based model debugging. Given task- or instance-level explanations, users can flexibly provide various forms of feedback via an intuitive, web-based UI. After receiving user feedback, XMD automatically updates the model in real time, by regularizing the model so that its explanations align with the user feedback. The new model can then be easily deployed into real-world applications via Hugging Face. Using XMD, we can improve the model's OOD performance on text classification tasks by up to 18%.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 45 of its 64 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

45 of 64 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  7. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  8. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  9. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  11. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  12. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
33 more
  1. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  2. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  3. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 422
  4. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 417
  5. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
  6. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  7. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  8. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 294
  9. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
  10. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 217
  11. 2018Hate Speech Dataset from a White Supremacy Forumcited by 198
  12. 2020Adversarial Filters of Dataset Biasescited by 160
  13. 2020Debugging Tests for Model Explanationscited by 147
  14. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
  15. 2019Towards Debiasing Fact Verification Modelscited by 143
  16. 2019Unlearn Dataset Bias in Natural Language Inference by Fitting the Residualcited by 119
  17. 2020Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performancecited by 85
  18. 2020Contextualizing Hate Speech Classifiers with Post-hoc Explanationcited by 84
  19. 2021Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Modelscited by 78
  20. 2019Incorporating Priors with Feature Attribution on Text Classificationcited by 68
  21. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  22. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40
  23. 2020Evaluating and Characterizing Human Rationalescited by 36
  24. 2021UNIREX: A Unified Learning Framework for Language Model Rationale Extractioncited by 32
  25. 2020TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognitioncited by 30
  26. 2021Refining Language Models with Compositional Explanationscited by 27
  27. 2022A Rationale-Centric Framework for Human-in-the-loop Machine Learningcited by 27
  28. 2019Saliency Learning: Teaching the Model Where to Pay Attentioncited by 23
  29. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  30. 2022A survey on improving NLP models with human explanationscited by 15
  31. 2020LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanationcited by 11
  32. 2021Towards Benchmarking the Utility of Explanations for Model Debuggingcited by 10
  33. 2021Exploring Distantly-Labeled Rationales in Neural Network Modelscited by 8

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5.

8 papers.

  1. 2023Explainability for Large Language Models: A Surveycited by 333
  2. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 111
  3. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 51
  4. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
  5. 2024LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanationscited by 16
  6. 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanationscited by 11
  7. 2024CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systemscited by 5
  8. 2023Analyzing Norm Violations in Live-Stream Chatcited by 3