mlsanityData to 7 Oct 2026

A survey on improving NLP models with human explanations

arXiv 2204.08892 ↗First posted 19 Apr 2022cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from explanations a promising way to establish a fruitful human-machine interaction. Several methods have been proposed for improving natural language processing (NLP) models with human explanations, that rely on different explanation types and mechanism for integrating these explanations into the learning process. These methods are rarely compared with each other, making it hard for practitioners to choose the best combination of explanation type and integration mechanism for a specific use-case. In this paper, we give an overview of different methods for learning from human explanations, and discuss different factors that can inform the decision of which method to choose for a specific use-case.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

33 of 51 references.

References · 33

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  3. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  4. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  5. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  6. 2016Rationalizing Neural Predictionscited by 281
  7. 2016Data Programming: Creating Large Training Sets, Quicklycited by 246
  8. 2020Measuring Association Between Labels and Free-Text Rationalescited by 159
  9. 2020A Diagnostic Study of Explainability Techniques for Text Classificationcited by 158
  10. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  11. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  12. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
21 more
  1. 2020NILE : Natural Language Inference with Faithful Natural Language Explanationscited by 96
  2. 2020Evaluating Explanations: How much do explanations from the teacher aid students?cited by 94
  3. 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
  4. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  5. 2019Incorporating Priors with Feature Attribution on Text Classificationcited by 68
  6. 2018Training Classifiers with Natural Language Explanationscited by 58
  7. 2018Deriving Machine Attention from Human Rationalescited by 54
  8. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  9. 2016Rationale-Augmented Convolutional Neural Networks for Text Classificationcited by 39
  10. 2020Evaluating and Characterizing Human Rationalescited by 36
  11. 2019Do Human Rationales Improve Machine Explanations?cited by 33
  12. 2021On the Diversity and Limits of Human Explanationscited by 30
  13. 2020ExpBERT: Representation Engineering with Natural Language Explanationscited by 28
  14. 2021Refining Language Models with Compositional Explanationscited by 27
  15. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  16. 2020LIREx: Augmenting Language Inference with Relevant Explanationcited by 24
  17. 2019Fine-grained Sentiment Analysis with Faithful Attentioncited by 23
  18. 2020Teaching Machine Comprehension with Compositional Explanationscited by 22
  19. 2019Learning from Explanations with Neural Execution Treecited by 18
  20. 2020LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanationcited by 11
  21. 2020Interacting with Explanations through Critiquingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 4; 2025: 4; 2026: 1.

15 papers.

Sort:

By area:

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  2. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  3. 2023Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanationscited by 12
  4. 2022XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Modelscited by 8
  5. 2022Mediators: Conversational Agents Explaining NLP Model Behaviorcited by 7
  6. 2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
  7. 2024Human-LLM Hybrid Text Answer Aggregation for Crowd Annotationscited by 4
  8. 2024EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correctioncited by 1
  9. 2024Explanation Regularisation through the Lens of Attributionscited by 1
  10. 2025Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategiescited by 1
  11. 2026Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detectioncited by 1
  12. 2023Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentationcited by 0
3 more
  1. 2025Emerging categories in scientific explanationscited by 0
  2. 2025Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Modelscited by 0
  3. 2025Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Studycited by 0