# Contrastive Explanations for Model Interpretability

arXiv: https://arxiv.org/abs/2103.01378 · HTML: https://mlsanity.com/paper/2103.01378/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 30 of 45)

- [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)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (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)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Visualizing Deep Neural Network Decisions: Prediction Difference Analysis](https://mlsanity.com/paper/1702.04595/) (2017)
- [Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?](https://mlsanity.com/paper/2005.00719/) (2020)

## Built on by (most cited first, 30 of 75)

- [ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning](https://mlsanity.com/paper/2212.07919/) (2022)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models](https://mlsanity.com/paper/2110.07736/) (2021)
- [Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction](https://mlsanity.com/paper/2105.06965/) (2021)
- [Probing Classifiers are Unreliable for Concept Removal and Detection](https://mlsanity.com/paper/2207.04153/) (2022)
- [Heterogeneous Contrastive Learning for Foundation Models and Beyond](https://mlsanity.com/paper/2404.00225/) (2024)
- [ECINN: Efficient Counterfactuals from Invertible Neural Networks](https://mlsanity.com/paper/2103.13701/) (2021)
- [Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant](https://mlsanity.com/paper/2501.17546/) (2025)
- [A Geometric Notion of Causal Probing](https://mlsanity.com/paper/2307.15054/) (2023)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Morae: Proactively Pausing UI Agents for User Choices](https://mlsanity.com/paper/2508.21456/) (2025)
- [Consistent Explanations by Contrastive Learning](https://mlsanity.com/paper/2110.00527/) (2021)
- [TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents](https://mlsanity.com/paper/2312.01279/) (2023)
- [Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills](https://mlsanity.com/paper/2410.04253/) (2024)
- [Investigating the Benefits of Free-Form Rationales](https://mlsanity.com/paper/2206.11083/) (2022)
- [The Dead Salmons of AI Interpretability](https://mlsanity.com/paper/2512.18792/) (2025)
- [Surfacing Biases in Large Language Models using Contrastive Input Decoding](https://mlsanity.com/paper/2305.07378/) (2023)
- [Rather a Nurse than a Physician -- Contrastive Explanations under Investigation](https://mlsanity.com/paper/2310.11906/) (2023)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [Interpretation of Black Box NLP Models: A Survey](https://mlsanity.com/paper/2203.17081/) (2022)
- [Lexical Generalization Improves with Larger Models and Longer Training](https://mlsanity.com/paper/2210.12673/) (2022)
- [Does Self-Rationalization Improve Robustness to Spurious Correlations?](https://mlsanity.com/paper/2210.13575/) (2022)
- [Learning with Instance Bundles for Reading Comprehension](https://mlsanity.com/paper/2104.08735/) (2021)
- [Contrastive Corpus Attribution for Explaining Representations](https://mlsanity.com/paper/2210.00107/) (2022)
- [Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features](https://mlsanity.com/paper/2309.07733/) (2023)

## Abstract (arXiv)

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification models by modifying the representation to disregard non-contrastive information, and modifying model behavior to only be based on contrastive reasoning. Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions. We demonstrate the value of contrastive explanations by analyzing two different scenarios, using both high-level abstract concept attribution and low-level input token/span attribution, on two widely used text classification tasks. Specifically, we produce explanations for answering: for which label, and against which alternative label, is some aspect of the input useful? And which aspects of the input are useful for and against particular decisions? Overall, our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.