# Explaining Text Classifiers with Counterfactual Representations

arXiv: https://arxiv.org/abs/2402.00711 · HTML: https://mlsanity.com/paper/2402.00711/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [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)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Adversarial Removal of Demographic Attributes from Text Data](https://mlsanity.com/paper/1808.06640/) (2018)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text](https://mlsanity.com/paper/2012.04698/) (2020)
- [CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior](https://mlsanity.com/paper/2205.14140/) (2022)
- [Kernelized Concept Erasure](https://mlsanity.com/paper/2201.12191/) (2022)
- [DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation](https://mlsanity.com/paper/2202.12350/) (2022)
- [Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information](https://mlsanity.com/paper/2203.07893/) (2022)
- [Robust Concept Erasure via Kernelized Rate-Distortion Maximization](https://mlsanity.com/paper/2312.00194/) (2023)

## Built on by (most cited first, 3 of 3)

- [Nonlinear Concept Erasure: a Density Matching Approach](https://mlsanity.com/paper/2507.12341/) (2025)
- [Counterfactually Fair Conformal Prediction](https://mlsanity.com/paper/2510.08724/) (2025)
- [MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions](https://mlsanity.com/paper/2609.11253/) (2026)

## Abstract (arXiv)

One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges for texts, however, as some attribute values may not necessarily align with plausible real-world events. In this paper we propose a simple method for generating counterfactuals by intervening in the space of text representations which bypasses this limitation. We argue that our interventions are minimally disruptive and that they are theoretically sound as they align with counterfactuals as defined in Pearl's causal inference framework. To validate our method, we conducted experiments first on a synthetic dataset and then on a realistic dataset of counterfactuals. This allows for a direct comparison between classifier predictions based on ground truth counterfactuals - obtained through explicit text interventions - and our counterfactuals, derived through interventions in the representation space. Eventually, we study a real world scenario where our counterfactuals can be leveraged both for explaining a classifier and for bias mitigation.