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

24 September 2021

Papers citing "Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding"

9 / 9 papers shown

Title
GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns Enzo Doyen Amalia Todirascu 53 0 0 29 May 2025
Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes Damin Zhang Yi Zhang Geetanjali Bihani Julia Taylor Rayz 162 3 0 06 May 2024
Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models Alapan Kuila Somnath Jena Sudeshna Sarkar P. Chakrabarti AAML 44 2 0 03 Feb 2024
Synthetic Pre-Training Tasks for Neural Machine Translation Zexue He Graeme W. Blackwood Yikang Shen Julian McAuley Rogerio Feris 56 4 0 19 Dec 2022
Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition Shuguang Chen Leonardo Neves Thamar Solorio 110 4 0 14 Oct 2022
Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey Sachin Kumar Vidhisha Balachandran Lucille Njoo Antonios Anastasopoulos Yulia Tsvetkov ELM 187 91 0 14 Oct 2022
Controlling Bias Exposure for Fair Interpretable Predictions Zexue He Yu Wang Julian McAuley Bodhisattwa Prasad Majumder 58 19 0 14 Oct 2022
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions Bodhisattwa Prasad Majumder Zexue He Julian McAuley 56 6 0 14 Oct 2022
Text Style Transfer for Bias Mitigation using Masked Language Modeling E. Tokpo T. Calders 64 35 0 21 Jan 2022