# Flexible text generation for counterfactual fairness probing

arXiv: https://arxiv.org/abs/2206.13757 · HTML: https://mlsanity.com/paper/2206.13757/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://mlsanity.com/paper/2109.03910/) (2021)
- [Explaining NLP Models via Minimal Contrastive Editing (MiCE)](https://mlsanity.com/paper/2012.13985/) (2020)
- [It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution](https://mlsanity.com/paper/1909.00871/) (2019)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text](https://mlsanity.com/paper/2012.04698/) (2020)
- [Perturbation Sensitivity Analysis to Detect Unintended Model Biases](https://mlsanity.com/paper/1910.04210/) (2019)
- [Tailor: Generating and Perturbing Text with Semantic Controls](https://mlsanity.com/paper/2107.07150/) (2021)
- [Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate](https://mlsanity.com/paper/2108.05921/) (2021)

## Built on by (most cited first, 13 of 13)

- [AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications](https://mlsanity.com/paper/2311.08592/) (2023)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration](https://mlsanity.com/paper/2309.07822/) (2023)
- [Is Your Large Language Model Knowledgeable or a Choices-Only Cheater?](https://mlsanity.com/paper/2407.01992/) (2024)
- [RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals](https://mlsanity.com/paper/2410.11348/) (2024)
- [Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models](https://mlsanity.com/paper/2305.11364/) (2023)
- [Language Models as Causal Effect Generators](https://mlsanity.com/paper/2411.08019/) (2024)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)
- [On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection](https://mlsanity.com/paper/2305.12829/) (2023)
- [Synthetic Text Generation using Hypergraph Representations](https://mlsanity.com/paper/2309.06550/) (2023)
- [Causal Inference for Human-Language Model Collaboration](https://mlsanity.com/paper/2404.00207/) (2024)
- [Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals](https://mlsanity.com/paper/2311.09605/) (2023)

## Abstract (arXiv)

A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed? Existing counterfactual generation methods typically rely on wordlists or templates, producing simple counterfactuals that don't take into account grammar, context, or subtle sensitive attribute references, and could miss issues that the wordlist creators had not considered. In this paper, we introduce a task for generating counterfactuals that overcomes these shortcomings, and demonstrate how large language models (LLMs) can be leveraged to make progress on this task. We show that this LLM-based method can produce complex counterfactuals that existing methods cannot, comparing the performance of various counterfactual generation methods on the Civil Comments dataset and showing their value in evaluating a toxicity classifier.