# UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

arXiv: https://arxiv.org/abs/2112.08802 · HTML: https://mlsanity.com/paper/2112.08802/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 76 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [Deep Learning Based Text Classification: A Comprehensive Review](https://mlsanity.com/paper/2004.03705/) (2020)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?](https://mlsanity.com/paper/2010.05607/) (2020)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)

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

- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales](https://mlsanity.com/paper/2211.01562/) (2022)
- [REV: Information-Theoretic Evaluation of Free-Text Rationales](https://mlsanity.com/paper/2210.04982/) (2022)
- [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)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)
- [TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents](https://mlsanity.com/paper/2312.01279/) (2023)
- [Enhancing the Rationale-Input Alignment for Self-explaining Rationalization](https://mlsanity.com/paper/2312.04103/) (2023)
- [Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint](https://mlsanity.com/paper/2305.13599/) (2023)
- [Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations](https://mlsanity.com/paper/2305.03117/) (2023)
- [MGR: Multi-generator Based Rationalization](https://mlsanity.com/paper/2305.04492/) (2023)
- [Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization](https://mlsanity.com/paper/2410.06003/) (2024)
- [Explainability in Practice: A Survey of Explainable NLP Across Various Domains](https://mlsanity.com/paper/2502.00837/) (2025)
- [FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales](https://mlsanity.com/paper/2207.00779/) (2022)
- [XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models](https://mlsanity.com/paper/2210.16978/) (2022)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models](https://mlsanity.com/paper/2311.01732/) (2023)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction](https://mlsanity.com/paper/2305.03503/) (2023)
- [Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization](https://mlsanity.com/paper/2503.06202/) (2025)
- [Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets](https://mlsanity.com/paper/2505.02118/) (2025)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [ExClaim: Explainable Neural Claim Verification Using Rationalization](https://mlsanity.com/paper/2301.08914/) (2023)
- [Give Me More Details: Improving Fact-Checking with Latent Retrieval](https://mlsanity.com/paper/2305.16128/) (2023)
- [REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization](https://mlsanity.com/paper/2310.14418/) (2023)
- [Noiser: Bounded Input Perturbations for Attributing Large Language Models](https://mlsanity.com/paper/2504.02911/) (2025)
- [CAVE: Controllable Authorship Verification Explanations](https://mlsanity.com/paper/2406.16672/) (2024)
- [Explanation Regularisation through the Lens of Attributions](https://mlsanity.com/paper/2407.16693/) (2024)
- [Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization](https://mlsanity.com/paper/2510.13393/) (2025)
- [Using Interpretation Methods for Model Enhancement](https://mlsanity.com/paper/2404.02068/) (2024)

## Abstract (arXiv)

An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual behavior) and plausible (convincing to humans), without compromising the LM's (i.e., task model's) task performance. Although attribution algorithms and select-predict pipelines are commonly used in rationale extraction, they both rely on certain heuristics that hinder them from satisfying all three desiderata. In light of this, we propose UNIREX, a flexible learning framework that generalizes rationale extractor optimization as follows: (1) specify architecture for a learned rationale extractor; (2) select explainability objectives (i.e., faithfulness and plausibility criteria); and (3) jointly the train task model and rationale extractor on the task using the selected objectives. UNIREX enables replacing prior works' heuristic design choices with a generic learned rationale extractor in (1) and optimizing it for all three desiderata in (2)-(3). To facilitate comparison between methods with respect to multiple desiderata, we introduce the Normalized Relative Gain (NRG) metric. Across five text classification datasets, our best UNIREX configuration outperforms baselines by an average of 32.9% NRG. Plus, we find that UNIREX-trained rationale extractors can even generalize to unseen datasets and tasks.