# Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification

arXiv: https://arxiv.org/abs/2105.02657 · HTML: https://mlsanity.com/paper/2105.02657/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 60 references that are in the map.
- First posted on arXiv 6 May 2021.

## Builds on (most cited first, 30 of 36)

- [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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [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)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (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)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Learning to Deceive with Attention-Based Explanations](https://mlsanity.com/paper/1909.07913/) (2019)
- [Explaining Recurrent Neural Network Predictions in Sentiment Analysis](https://mlsanity.com/paper/1706.07206/) (2017)
- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [Attention Interpretability Across NLP Tasks](https://mlsanity.com/paper/1909.11218/) (2019)

## Built on by (most cited first, 29 of 29)

- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Rethinking Attention-Model Explainability through Faithfulness Violation Test](https://mlsanity.com/paper/2201.12114/) (2022)
- [A Comparative Study of Faithfulness Metrics for Model Interpretability Methods](https://mlsanity.com/paper/2204.05514/) (2022)
- [Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience](https://mlsanity.com/paper/2108.13759/) (2021)
- [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)
- [The Solvability of Interpretability Evaluation Metrics](https://mlsanity.com/paper/2205.08696/) (2022)
- [Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure](https://mlsanity.com/paper/2602.08783/) (2026)
- [Towards a Framework for Evaluating Explanations in Automated Fact Verification](https://mlsanity.com/paper/2403.20322/) (2024)
- [Plausible Extractive Rationalization through Semi-Supervised Entailment Signal](https://mlsanity.com/paper/2402.08479/) (2024)
- [PromptExp: Multi-granularity Prompt Explanation of Large Language Models](https://mlsanity.com/paper/2410.13073/) (2024)
- [Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media](https://mlsanity.com/paper/2204.10080/) (2022)
- [Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint](https://mlsanity.com/paper/2406.04612/) (2024)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)
- [Learning to Explain: Prototype-Based Surrogate Models for LLM Classification](https://mlsanity.com/paper/2505.18970/) (2025)
- [Towards Transparent AI: A Survey on Explainable Language Models](https://mlsanity.com/paper/2509.21631/) (2025)
- [SPADE: Sparsity-Guided Debugging for Deep Neural Networks](https://mlsanity.com/paper/2310.04519/) (2023)
- [On Explaining with Attention Matrices](https://mlsanity.com/paper/2410.18541/) (2024)
- [From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models](https://mlsanity.com/paper/2501.14731/) (2024)
- [Truthful Meta-Explanations for Local Interpretability of Machine Learning Models](https://mlsanity.com/paper/2212.03513/) (2022)
- [Evaluating Explanation Methods for Vision-and-Language Navigation](https://mlsanity.com/paper/2310.06654/) (2023)
- [Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection](https://mlsanity.com/paper/2209.08681/) (2022)
- [Noise-Free Explanation for Driving Action Prediction](https://mlsanity.com/paper/2407.06339/) (2024)
- [PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification](https://mlsanity.com/paper/2507.10596/) (2025)
- [An Experimental Study on Generating Plausible Textual Explanations for Video Summarization](https://mlsanity.com/paper/2509.26225/) (2025)
- [Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian](https://mlsanity.com/paper/2511.19719/) (2025)
- [ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection](https://mlsanity.com/paper/2604.12321/) (2026)
- [Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG](https://mlsanity.com/paper/2606.01482/) (2026)

## Abstract (arXiv)

Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various tasks, while its weights have been extensively used as explanations for model predictions. Recent studies (Jain and Wallace, 2019; Serrano and Smith, 2019; Wiegreffe and Pinter, 2019) have showed that it cannot generally be considered as a faithful explanation (Jacovi and Goldberg, 2020) across encoders and tasks. In this paper, we seek to improve the faithfulness of attention-based explanations for text classification. We achieve this by proposing a new family of Task-Scaling (TaSc) mechanisms that learn task-specific non-contextualised information to scale the original attention weights. Evaluation tests for explanation faithfulness, show that the three proposed variants of TaSc improve attention-based explanations across two attention mechanisms, five encoders and five text classification datasets without sacrificing predictive performance. Finally, we demonstrate that TaSc consistently provides more faithful attention-based explanations compared to three widely-used interpretability techniques.