# Flexible Instance-Specific Rationalization of NLP Models

arXiv: https://arxiv.org/abs/2104.08219 · HTML: https://mlsanity.com/paper/2104.08219/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (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)
- [Explaining Recurrent Neural Network Predictions in Sentiment Analysis](https://mlsanity.com/paper/1706.07206/) (2017)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [Interpretation of NLP models through input marginalization](https://mlsanity.com/paper/2010.13984/) (2020)
- [Explaining Predictions of Non-Linear Classifiers in NLP](https://mlsanity.com/paper/1606.07298/) (2016)
- [Evaluating and Characterizing Human Rationales](https://mlsanity.com/paper/2010.04736/) (2020)
- [Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers](https://mlsanity.com/paper/2010.00667/) (2020)

## Built on by (most cited first, 10 of 10)

- [On the Impact of Temporal Concept Drift on Model Explanations](https://mlsanity.com/paper/2210.09197/) (2022)
- [Incorporating Attribution Importance for Improving Faithfulness Metrics](https://mlsanity.com/paper/2305.10496/) (2023)
- [ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models](https://mlsanity.com/paper/2402.00794/) (2024)
- [On Evaluating Explanation Utility for Human-AI Decision Making in NLP](https://mlsanity.com/paper/2407.03545/) (2024)
- [Towards a Framework for Evaluating Explanations in Automated Fact Verification](https://mlsanity.com/paper/2403.20322/) (2024)
- [Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media](https://mlsanity.com/paper/2204.10080/) (2022)
- [CMA-R:Causal Mediation Analysis for Explaining Rumour Detection](https://mlsanity.com/paper/2402.08155/) (2024)
- [Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection](https://mlsanity.com/paper/2209.08681/) (2022)
- [Moral Sparks in Social Media Narratives](https://mlsanity.com/paper/2310.19268/) (2023)
- [Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification](https://mlsanity.com/paper/2601.12419/) (2026)

## Abstract (arXiv)

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or rationale). However, previous research has shown that there is no clear best scoring method across various text classification tasks while practitioners typically have to make several other ad-hoc choices regarding the length and the type of the rationale (e.g. short or long, contiguous or not). Inspired by this, we propose a simple yet effective and flexible method that allows selecting optimally for each data instance: (1) a feature scoring method; (2) the length; and (3) the type of the rationale. Our method is inspired by input erasure approaches to interpretability which assume that the most faithful rationale for a prediction should be the one with the highest difference between the model's output distribution using the full text and the text after removing the rationale as input respectively. Evaluation on four standard text classification datasets shows that our proposed method provides more faithful, comprehensive and highly sufficient explanations compared to using a fixed feature scoring method, rationale length and type. More importantly, we demonstrate that a practitioner is not required to make any ad-hoc choices in order to extract faithful rationales using our approach.