# Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding

arXiv: https://arxiv.org/abs/2109.11708 · HTML: https://mlsanity.com/paper/2109.11708/

## Key facts

- Cited by 23 papers in the map (data through 7 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 24 Sep 2021.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [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)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem](https://mlsanity.com/paper/2004.04498/) (2020)
- [Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation](https://mlsanity.com/paper/1905.05621/) (2019)
- [Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer](https://mlsanity.com/paper/1908.09368/) (2019)
- [PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction](https://mlsanity.com/paper/2010.13816/) (2020)
- [Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning](https://mlsanity.com/paper/2009.13028/) (2020)
- [Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge](https://mlsanity.com/paper/2104.06828/) (2021)
- [Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders](https://mlsanity.com/paper/1911.03882/) (2019)
- [Adversarial Decomposition of Text Representation](https://mlsanity.com/paper/1808.09042/) (2018)
- [Unsupervised Enrichment of Persona-grounded Dialog with Background Stories](https://mlsanity.com/paper/2106.08364/) (2021)
- [Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting](https://mlsanity.com/paper/2101.00416/) (2021)

## Built on by (most cited first, 23 of 23)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Text Style Transfer for Bias Mitigation using Masked Language Modeling](https://mlsanity.com/paper/2201.08643/) (2022)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation](https://mlsanity.com/paper/2310.14088/) (2023)
- [Controlling Bias Exposure for Fair Interpretable Predictions](https://mlsanity.com/paper/2210.07455/) (2022)
- [Targeted Data Generation: Finding and Fixing Model Weaknesses](https://mlsanity.com/paper/2305.17804/) (2023)
- [Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies](https://mlsanity.com/paper/2312.01509/) (2023)
- [The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias](https://mlsanity.com/paper/2312.16148/) (2023)
- [Potential and Challenges of Model Editing for Social Debiasing](https://mlsanity.com/paper/2402.13462/) (2024)
- [Synthetic Pre-Training Tasks for Neural Machine Translation](https://mlsanity.com/paper/2212.09864/) (2022)
- [InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions](https://mlsanity.com/paper/2210.07440/) (2022)
- [Quantifying Cognitive Bias Induction in LLM-Generated Content](https://mlsanity.com/paper/2507.03194/) (2025)
- [Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes](https://mlsanity.com/paper/2405.06687/) (2024)
- [Mitigating Gender Bias in Code Large Language Models via Model Editing](https://mlsanity.com/paper/2410.07820/) (2024)
- [Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition](https://mlsanity.com/paper/2210.07916/) (2022)
- ["Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion](https://mlsanity.com/paper/2305.08300/) (2023)
- [LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models](https://mlsanity.com/paper/2505.15475/) (2025)
- [Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models](https://mlsanity.com/paper/2402.02145/) (2024)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns](https://mlsanity.com/paper/2505.23630/) (2025)
- [DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models](https://mlsanity.com/paper/2503.19426/) (2025)

## Abstract (arXiv)

Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates differently, or their writing style may indirectly reveal demographic characteristics. At best, such biases distract from the meaningful content of the text; at worst they can lead to unfair outcomes. We investigate the challenge of re-generating input sentences to 'neutralize' sensitive attributes while maintaining the semantic meaning of the original text (e.g. is the candidate qualified?). We propose a gradient-based rewriting framework, Detect and Perturb to Neutralize (DEPEN), that first detects sensitive components and masks them for regeneration, then perturbs the generation model at decoding time under a neutralizing constraint that pushes the (predicted) distribution of sensitive attributes towards a uniform distribution. Our experiments in two different scenarios show that DEPEN can regenerate fluent alternatives that are neutral in the sensitive attribute while maintaining the semantics of other attributes.