# Text Counterfactuals via Latent Optimization and Shapley-Guided Search

arXiv: https://arxiv.org/abs/2110.11589 · HTML: https://mlsanity.com/paper/2110.11589/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 22 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [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)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Towards Efficient Data Valuation Based on the Shapley Value](https://mlsanity.com/paper/1902.10275/) (2019)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Contextualized Perturbation for Textual Adversarial Attack](https://mlsanity.com/paper/2009.07502/) (2020)
- [L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data](https://mlsanity.com/paper/1808.02610/) (2018)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer](https://mlsanity.com/paper/1908.09368/) (2019)
- [There and Back Again: Revisiting Backpropagation Saliency Methods](https://mlsanity.com/paper/2004.02866/) (2020)
- [Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification](https://mlsanity.com/paper/2010.12512/) (2020)
- [Word-level Textual Adversarial Attacking as Combinatorial Optimization](https://mlsanity.com/paper/1910.12196/) (2019)
- [Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation](https://mlsanity.com/paper/1905.12926/) (2019)

## Built on by (most cited first, 16 of 16)

- [Counterfactual Shapley Additive Explanations](https://mlsanity.com/paper/2110.14270/) (2021)
- [A Survey on Natural Language Counterfactual Generation](https://mlsanity.com/paper/2407.03993/) (2024)
- ["FIJO": a French Insurance Soft Skill Detection Dataset](https://mlsanity.com/paper/2204.05208/) (2022)
- [TIGTEC : Token Importance Guided TExt Counterfactuals](https://mlsanity.com/paper/2304.12425/) (2023)
- [Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values](https://mlsanity.com/paper/2303.01928/) (2023)
- [Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval](https://mlsanity.com/paper/2501.04802/) (2025)
- [Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors](https://mlsanity.com/paper/2305.17055/) (2023)
- [A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution](https://mlsanity.com/paper/2404.01921/) (2024)
- [A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers](https://mlsanity.com/paper/2411.02643/) (2024)
- [Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals](https://mlsanity.com/paper/2505.13972/) (2025)
- [Guiding LLMs to Generate High-Fidelity and High-Quality Counterfactual Explanations for Text Classification](https://mlsanity.com/paper/2503.04463/) (2025)
- [A General Search-based Framework for Generating Textual Counterfactual Explanations](https://mlsanity.com/paper/2211.00369/) (2022)
- [Mitigating Text Toxicity with Counterfactual Generation](https://mlsanity.com/paper/2405.09948/) (2024)
- [Explaining Recommendation System Using Counterfactual Textual Explanations](https://mlsanity.com/paper/2303.11160/) (2023)
- [DRIV-EX: Counterfactual Explanations for Driving LLMs](https://mlsanity.com/paper/2603.00696/) (2026)
- [Automatically Generating Counterfactuals for Relation Classification](https://mlsanity.com/paper/2202.10668/) (2022)

## Abstract (arXiv)

We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model's prediction. White-box approaches have been successfully applied to similar problems in vision where one can directly optimize the continuous input. Optimization-based approaches become difficult in the language domain due to the discrete nature of text. We bypass this issue by directly optimizing in the latent space and leveraging a language model to generate candidate modifications from optimized latent representations. We additionally use Shapley values to estimate the combinatoric effect of multiple changes. We then use these estimates to guide a beam search for the final counterfactual text. We achieve favorable performance compared to recent white-box and black-box baselines using human and automatic evaluations. Ablation studies show that both latent optimization and the use of Shapley values improve success rate and the quality of the generated counterfactuals.