mlsanityData to 13 Oct 2026

A Rationale-Centric Framework for Human-in-the-loop Machine Learning

arXiv 2203.12918 ↗First posted 24 Mar 2022cs.AI cs.CL cs.HCcited by 27

Not on the map. Why?

Abstract (arXiv)

We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests compared to many state-of-the-art benchmarks -- especially for few-shot learning scenarios. We also perform extensive ablation studies to support in-depth analyses of each component in our framework.

Key facts. Cited by 27 papers in the map (data through 13 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

27 of 48 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  3. 2015Character-level Convolutional Networks for Text Classificationcited by 2,319
  4. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 802
  5. 2018Annotation Artifacts in Natural Language Inference Datacited by 664
  6. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  7. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 433
  8. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  9. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 209
  10. 2021Active Learning by Acquiring Contrastive Examplescited by 155
  11. 2020An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Modelscited by 134
  12. 2020Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanationscited by 94
15 more
  1. 2021Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Modelscited by 76
  2. 2020Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactualscited by 67
  3. 2020Explaining The Efficacy of Counterfactually Augmented Datacited by 64
  4. 2020Robustness to Spurious Correlations via Human Annotationscited by 62
  5. 2020On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learningcited by 60
  6. 2020Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimatescited by 59
  7. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  8. 2021Interactive Label Cleaning with Example-based Explanationscited by 48
  9. 2020FIND: Human-in-the-Loop Debugging Deep Text Classifierscited by 40
  10. 2020Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classificationcited by 40
  11. 2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
  12. 2021Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutionscited by 16
  13. 2021Empowering Language Understanding with Counterfactual Reasoningcited by 13
  14. 2020Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasetscited by 6
  15. 2021A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Datacited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 8; 2023: 8; 2024: 8; 2025: 1; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 313
  2. 2022GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspectivecited by 72
  3. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  4. 2024Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Modelscited by 30
  5. 2022What Makes Pre-trained Language Models Better Zero-shot Learners?cited by 23
  6. 2023Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAIcited by 20
  7. 2023Supervised Knowledge Makes Large Language Models Better In-context Learnerscited by 20
  8. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  9. 2022PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasetscited by 10
  10. 2022XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Modelscited by 8
  11. 2023The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomescited by 8
  12. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7
15 more
  1. 2024A Survey on Human-AI Collaboration with Large Foundation Modelscited by 7
  2. 2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
  3. 2023Learning to Generalize for Cross-domain QAcited by 6
  4. 2024PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognitioncited by 6
  5. 2024Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?cited by 5
  6. 2025Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentencescited by 5
  7. 2023RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answeringcited by 4
  8. 2022Exploiting Unlabeled Data for Target-Oriented Opinion Words Extractioncited by 2
  9. 2024Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discoverycited by 2
  10. 2024EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversariescited by 2
  11. 2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
  12. 2023CR-COPEC: Causal Rationale of Corporate Performance Changes to Learn from Financial Reportscited by 1
  13. 2024DISCO: DISCovering Overfittings as Causal Rules for Text Classification Modelscited by 0
  14. 2026Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefercited by 0
  15. 2026Semifactual Credit-Augmented Policy Optimizationcited by 0