# Explaining NLP Models via Minimal Contrastive Editing (MiCE)

arXiv: https://arxiv.org/abs/2012.13985 · HTML: https://mlsanity.com/paper/2012.13985/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2020.

## Built on by (most cited first, 30 of 106)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Are self-explanations from Large Language Models faithful?](https://mlsanity.com/paper/2401.07927/) (2024)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [Tailor: Generating and Perturbing Text with Semantic Controls](https://mlsanity.com/paper/2107.07150/) (2021)
- ["Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification](https://mlsanity.com/paper/2111.07367/) (2021)
- [Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction](https://mlsanity.com/paper/2105.06965/) (2021)
- [Prompting Contrastive Explanations for Commonsense Reasoning Tasks](https://mlsanity.com/paper/2106.06823/) (2021)
- [A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives](https://mlsanity.com/paper/2102.12982/) (2021)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Prompting Large Language Models for Counterfactual Generation: An Empirical Study](https://mlsanity.com/paper/2305.14791/) (2023)
- [Understanding Interlocking Dynamics of Cooperative Rationalization](https://mlsanity.com/paper/2110.13880/) (2021)
- [Interpreting Pretrained Language Models via Concept Bottlenecks](https://mlsanity.com/paper/2311.05014/) (2023)
- [ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing](https://mlsanity.com/paper/2305.09770/) (2023)
- [LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study](https://mlsanity.com/paper/2405.00722/) (2024)
- [Retrieval-guided Counterfactual Generation for QA](https://mlsanity.com/paper/2110.07596/) (2021)
- [ferret: a Framework for Benchmarking Explainers on Transformers](https://mlsanity.com/paper/2208.01575/) (2022)
- [Counterfactual Explanations for Models of Code](https://mlsanity.com/paper/2111.05711/) (2021)
- [People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection](https://mlsanity.com/paper/2311.01270/) (2023)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [CREST: A Joint Framework for Rationalization and Counterfactual Text Generation](https://mlsanity.com/paper/2305.17075/) (2023)
- [A Survey on Natural Language Counterfactual Generation](https://mlsanity.com/paper/2407.03993/) (2024)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)

## Abstract (arXiv)

Humans have been shown to give contrastive explanations, which explain why an observed event happened rather than some other counterfactual event (the contrast case). Despite the influential role that contrastivity plays in how humans explain, this property is largely missing from current methods for explaining NLP models. We present Minimal Contrastive Editing (MiCE), a method for producing contrastive explanations of model predictions in the form of edits to inputs that change model outputs to the contrast case. Our experiments across three tasks--binary sentiment classification, topic classification, and multiple-choice question answering--show that MiCE is able to produce edits that are not only contrastive, but also minimal and fluent, consistent with human contrastive edits. We demonstrate how MiCE edits can be used for two use cases in NLP system development--debugging incorrect model outputs and uncovering dataset artifacts--and thereby illustrate that producing contrastive explanations is a promising research direction for model interpretability.