# A General Search-based Framework for Generating Textual Counterfactual Explanations

arXiv: https://arxiv.org/abs/2211.00369 · HTML: https://mlsanity.com/paper/2211.00369/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 1 Nov 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [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)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Model-Agnostic Counterfactual Explanations for Consequential Decisions](https://mlsanity.com/paper/1905.11190/) (2019)
- [Explaining NLP Models via Minimal Contrastive Editing (MiCE)](https://mlsanity.com/paper/2012.13985/) (2020)
- [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)
- [Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals](https://mlsanity.com/paper/2103.11972/) (2021)
- [Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification](https://mlsanity.com/paper/2010.12512/) (2020)
- [Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach](https://mlsanity.com/paper/2001.07417/) (2020)
- [Text Counterfactuals via Latent Optimization and Shapley-Guided Search](https://mlsanity.com/paper/2110.11589/) (2021)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [Weight of Evidence as a Basis for Human-Oriented Explanations](https://mlsanity.com/paper/1910.13503/) (2019)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [Textual Membership Queries](https://mlsanity.com/paper/1805.04609/) (2018)

## Built on by (most cited first, 2 of 2)

- [Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations](https://mlsanity.com/paper/2510.21631/) (2025)
- [Model of models -- Part 1](https://mlsanity.com/paper/2308.04600/) (2023)

## Abstract (arXiv)

One of the prominent methods for explaining the decision of a machine-learning classifier is by a counterfactual example. Most current algorithms for generating such examples in the textual domain are based on generative language models. Generative models, however, are trained to minimize a specific loss function in order to fulfill certain requirements for the generated texts. Any change in the requirements may necessitate costly retraining, thus potentially limiting their applicability. In this paper, we present a general search-based framework for generating counterfactual explanations in the textual domain. Our framework is model-agnostic, domain-agnostic, anytime, and does not require retraining in order to adapt to changes in the user requirements. We model the task as a search problem in a space where the initial state is the classified text, and the goal state is a text in a given target class. Our framework includes domain-independent modification operators, but can also exploit domain-specific knowledge through specialized operators. The search algorithm attempts to find a text from the target class with minimal user-specified distance from the original classified object.