Research map / Label-efficient and robust learning / Recognition and long-tail
A Game Theoretic Approach to Class-wise Selective Rationalization
Shiyu Chang, Yang Zhang, Mo Yu, Tommi Jaakkola
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use class-wise adversarial rationalization rather than RNP or Post-exp | CAR · Amazon Book and Electronic factual rationales | F1: 39.8 -> 43.6; 38.8 -> 46.4 | Improved |
| Use CAR rather than Post-exp to generate counterfactual rationales | Amazon Book and Electronic · Amazon counterfactual rationales | precision: + | Improved |
| Use CAR rather than the strongest baseline | CAR · Beer and Hotel factual rationales | F1: 57.3 -> 40.1; 47.5 -> 50.9; 48.6 -> 51.7; 39.1 -> 41.1; 33.0 -> 33.9 | Mixed |
Closest papers by meaning
- Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets (ICML 2025 · similarity 0.86)
- Learning Robust Rationales for Model Explainability: A Guidance-Based Approach (AAAI 2024 · similarity 0.85)
- Inverse Constitutional AI: Compressing Preferences into Principles (ICLR 2025 · similarity 0.83)
- Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery (ICLR 2024 · similarity 0.83)
- Tailoring Self-Rationalizers with Multi-Reward Distillation (ICLR 2024 · similarity 0.83)
- Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks (ICML 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
