# A Game Theoretic Approach to Class-wise Selective Rationalization

arXiv: https://arxiv.org/abs/1910.12853 · HTML: https://mlsanity.com/paper/1910.12853/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 30 of 32)

- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [Understanding Interlocking Dynamics of Cooperative Rationalization](https://mlsanity.com/paper/2110.13880/) (2021)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [Learning to Give Checkable Answers with Prover-Verifier Games](https://mlsanity.com/paper/2108.12099/) (2021)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [Rationalization for Explainable NLP: A Survey](https://mlsanity.com/paper/2301.08912/) (2023)
- [D-Separation for Causal Self-Explanation](https://mlsanity.com/paper/2309.13391/) (2023)
- [Rationalization through Concepts](https://mlsanity.com/paper/2105.04837/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)
- [FR: Folded Rationalization with a Unified Encoder](https://mlsanity.com/paper/2209.08285/) (2022)
- [COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks](https://mlsanity.com/paper/2305.06754/) (2023)
- [Enhancing the Rationale-Input Alignment for Self-explaining Rationalization](https://mlsanity.com/paper/2312.04103/) (2023)
- [Distribution Matching for Rationalization](https://mlsanity.com/paper/2106.00320/) (2021)
- [Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint](https://mlsanity.com/paper/2305.13599/) (2023)
- [Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations](https://mlsanity.com/paper/2101.10726/) (2021)
- [MGR: Multi-generator Based Rationalization](https://mlsanity.com/paper/2305.04492/) (2023)
- [Making a (Counterfactual) Difference One Rationale at a Time](https://mlsanity.com/paper/2201.05177/) (2022)
- [Interpretability Guarantees with Merlin-Arthur Classifiers](https://mlsanity.com/paper/2206.00759/) (2022)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [On the Interplay between Fairness and Explainability](https://mlsanity.com/paper/2310.16607/) (2023)
- [Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets](https://mlsanity.com/paper/2505.02118/) (2025)
- [GNN Explanations that do not Explain and How to find Them](https://mlsanity.com/paper/2601.20815/) (2026)
- [Rationalizing Predictions by Adversarial Information Calibration](https://mlsanity.com/paper/2301.06009/) (2023)
- [MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction](https://mlsanity.com/paper/2410.03531/) (2024)
- [Unsupervised Selective Rationalization with Noise Injection](https://mlsanity.com/paper/2305.17534/) (2023)
- [You Only Forward Once: Prediction and Rationalization in A Single Forward Pass](https://mlsanity.com/paper/2311.02344/) (2023)
- [Interlock-Free Multi-Aspect Rationalization for Text Classification](https://mlsanity.com/paper/2205.06756/) (2022)
- [Model Interpretability and Rationale Extraction by Input Mask Optimization](https://mlsanity.com/paper/2508.11388/) (2025)
- [Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization](https://mlsanity.com/paper/2510.13393/) (2025)

## Abstract (arXiv)

Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into the method itself (self-explaining). However, an overall selection does not properly capture the multi-faceted nature of useful rationales such as pros and cons for decisions. To this end, we propose a new game theoretic approach to class-dependent rationalization, where the method is specifically trained to highlight evidence supporting alternative conclusions. Each class involves three players set up competitively to find evidence for factual and counterfactual scenarios. We show theoretically in a simplified scenario how the game drives the solution towards meaningful class-dependent rationales. We evaluate the method in single- and multi-aspect sentiment classification tasks and demonstrate that the proposed method is able to identify both factual (justifying the ground truth label) and counterfactual (countering the ground truth label) rationales consistent with human rationalization. The code for our method is publicly available.