mlsanityData to 7 Oct 2026

Rationalizing Neural Predictions

arXiv 1606.04155 ↗First posted 13 Jun 2016cs.CL cs.NEcited by 281

Not on the map. Why?

Abstract (arXiv)

Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction. Our approach combines two modular components, generator and encoder, which are trained to operate well together. The generator specifies a distribution over text fragments as candidate rationales and these are passed through the encoder for prediction. Rationales are never given during training. Instead, the model is regularized by desiderata for rationales. We evaluate the approach on multi-aspect sentiment analysis against manually annotated test cases. Our approach outperforms attention-based baseline by a significant margin. We also successfully illustrate the method on the question retrieval task.

Key facts. Cited by 281 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 75; 2022: 69; 2023: 47; 2024: 30; 2025: 36; 2026: 24.

281 papers.

Sort:

By area:

  1. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  2. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 205
  3. 2022A Review on Language Models as Knowledge Basescited by 156
  4. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
  5. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 140
  6. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  7. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  8. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  9. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  10. 2024Are self-explanations from Large Language Models faithful?cited by 101
  11. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  12. 2021Implicit MLE: Backpropagating Through Discrete Exponential Family Distributionscited by 97
38 more
  1. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  2. 2021Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Casescited by 77
  3. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  4. 2022GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspectivecited by 72
  5. 2022Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderationcited by 66
  6. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  7. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 52
  8. 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
  9. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  10. 2021SelfExplain: A Self-Explaining Architecture for Neural Text Classifierscited by 44
  11. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  12. 2023Quantifying Context Mixing in Transformerscited by 43
  13. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  14. 2022CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checkingcited by 37
  15. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  16. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  17. 2022Can Rationalization Improve Robustness?cited by 36
  18. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  19. 2023Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Modelscited by 35
  20. 2022SIMPLE: A Gradient Estimator for k-Subset Samplingcited by 34
  21. 2021UNIREX: A Unified Learning Framework for Language Model Rationale Extractioncited by 32
  22. 2021Local Interpretations for Explainable Natural Language Processing: A Surveycited by 31
  23. 2023ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writingcited by 31
  24. 2021Explain and Predict, and then Predict Againcited by 29
  25. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  26. 2021Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behaviorcited by 29
  27. 2021Learning to Give Checkable Answers with Prover-Verifier Gamescited by 29
  28. 2021The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Resultscited by 27
  29. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?cited by 27
  30. 2021Rationales for Sequential Predictionscited by 26
  31. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  32. 2022Human Interpretation of Saliency-based Explanation Over Textcited by 25
  33. 2024Mechanistic?cited by 25
  34. 2021Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanationscited by 24
  35. 2023CREST: A Joint Framework for Rationalization and Counterfactual Text Generationcited by 24
  36. 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Functioncited by 24
  37. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  38. 2021Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoningcited by 23

50 most cited of 281 All 281 (JSON)