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

arXiv: https://arxiv.org/abs/2203.12918 · HTML: https://mlsanity.com/paper/2203.12918/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models](https://mlsanity.com/paper/2110.07736/) (2021)
- [Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals](https://mlsanity.com/paper/2012.10040/) (2020)
- [Explaining The Efficacy of Counterfactually Augmented Data](https://mlsanity.com/paper/2010.02114/) (2020)
- [Robustness to Spurious Correlations via Human Annotations](https://mlsanity.com/paper/2007.06661/) (2020)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [Explanation-Based Human Debugging of NLP Models: A Survey](https://mlsanity.com/paper/2104.15135/) (2021)
- [Interactive Label Cleaning with Example-based Explanations](https://mlsanity.com/paper/2106.03922/) (2021)
- [FIND: Human-in-the-Loop Debugging Deep Text Classifiers](https://mlsanity.com/paper/2010.04987/) (2020)
- [Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification](https://mlsanity.com/paper/2010.12512/) (2020)
- [Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis](https://mlsanity.com/paper/2106.15231/) (2021)
- [Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions](https://mlsanity.com/paper/2107.09734/) (2021)
- [Empowering Language Understanding with Counterfactual Reasoning](https://mlsanity.com/paper/2106.03046/) (2021)
- [Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets](https://mlsanity.com/paper/2004.13138/) (2020)
- [A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data](https://mlsanity.com/paper/2106.06738/) (2021)

## Built on by (most cited first, 27 of 27)

- [PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization](https://mlsanity.com/paper/2306.05087/) (2023)
- [GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective](https://mlsanity.com/paper/2211.08073/) (2022)
- [Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement](https://mlsanity.com/paper/2204.13074/) (2022)
- [Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models](https://mlsanity.com/paper/2405.15574/) (2024)
- [What Makes Pre-trained Language Models Better Zero-shot Learners?](https://mlsanity.com/paper/2209.15206/) (2022)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [Supervised Knowledge Makes Large Language Models Better In-context Learners](https://mlsanity.com/paper/2312.15918/) (2023)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets](https://mlsanity.com/paper/2211.14838/) (2022)
- [XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models](https://mlsanity.com/paper/2210.16978/) (2022)
- [The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes](https://mlsanity.com/paper/2310.18937/) (2023)
- [FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition](https://mlsanity.com/paper/2208.11464/) (2022)
- [A Survey on Human-AI Collaboration with Large Foundation Models](https://mlsanity.com/paper/2403.04931/) (2024)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Learning to Generalize for Cross-domain QA](https://mlsanity.com/paper/2305.08208/) (2023)
- [PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition](https://mlsanity.com/paper/2402.04838/) (2024)
- [Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?](https://mlsanity.com/paper/2403.00980/) (2024)
- [Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences](https://mlsanity.com/paper/2501.06795/) (2025)
- [RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2305.17041/) (2023)
- [Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction](https://mlsanity.com/paper/2208.08280/) (2022)
- [Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery](https://mlsanity.com/paper/2401.06327/) (2024)
- [EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries](https://mlsanity.com/paper/2402.13372/) (2024)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [CR-COPEC: Causal Rationale of Corporate Performance Changes to Learn from Financial Reports](https://mlsanity.com/paper/2310.16095/) (2023)
- [DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models](https://mlsanity.com/paper/2411.04649/) (2024)
- [Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer](https://mlsanity.com/paper/2603.17534/) (2026)
- [Semifactual Credit-Augmented Policy Optimization](https://mlsanity.com/paper/2609.40360/) (2026)

## 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.