# Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers

arXiv: https://arxiv.org/abs/2507.21186 · HTML: https://mlsanity.com/paper/2507.21186/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

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

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers](https://mlsanity.com/paper/2205.03286/) (2022)
- [Quantifying Context Mixing in Transformers](https://mlsanity.com/paper/2301.12971/) (2023)
- [Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps](https://mlsanity.com/paper/2204.11073/) (2022)
- [Understanding Individual Decisions of CNNs via Contrastive Backpropagation](https://mlsanity.com/paper/1812.02100/) (2018)
- [Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience](https://mlsanity.com/paper/2108.13759/) (2021)
- [Telling BERT's full story: from Local Attention to Global Aggregation](https://mlsanity.com/paper/2004.05916/) (2020)
- [Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings](https://mlsanity.com/paper/2012.15353/) (2020)

## Built on by (most cited first, 1 of 1)

- [Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models](https://mlsanity.com/paper/2602.16608/) (2026)

## Abstract (arXiv)

Transformers have profoundly influenced AI research, but explaining their decisions remains challenging -- even for relatively simpler tasks such as classification -- which hinders trust and safe deployment in real-world applications. Although activation-based attribution methods effectively explain transformer-based text classification models, our findings reveal that these methods can be undermined by class-irrelevant features within activations, leading to less reliable interpretations. To address this limitation, we propose Contrast-CAT, a novel activation contrast-based attribution method that refines token-level attributions by filtering out class-irrelevant features. By contrasting the activations of an input sequence with reference activations, Contrast-CAT generates clearer and more faithful attribution maps. Experimental results across various datasets and models confirm that Contrast-CAT consistently outperforms state-of-the-art methods. Notably, under the MoRF setting, it achieves average improvements of x1.30 in AOPC and x2.25 in LOdds over the most competing methods, demonstrating its effectiveness in enhancing interpretability for transformer-based text classification.