Citation map · Study

SZodixStudyAcademic Library

Shelves Open access

Study · an open academic library·Metadata from OpenAlex (CC0)·Shelves·OpenAlex metadata, de-duplicated

FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

13 references·13 citing·40 second hop

FromToDepth

this work references cited by second hop

References

2019HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case16,511 cited
2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings1,615 cited
2019MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations1,413 cited
2018Measuring and Mitigating Unintended Bias in Text Classification668 cited
2019On Measuring Social Biases in Sentence Encoders461 cited
2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems384 cited
2019Measuring Bias in Contextualized Word Representations348 cited
2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings262 cited
2019Identifying and Reducing Gender Bias in Word-Level Language Models219 cited
2020Towards Debiasing Sentence Representations154 cited
2018Understanding the Origins of Bias in Word Embeddings119 cited
2019Gender-preserving Debiasing for Pre-trained Word Embeddings113 cited
2018Learning Controllable Fair Representations94 cited

Cited by

2023Unlearning Bias in Language Models by Partitioning Gradients45 cited
2023

Only edges whose both ends are imported exist here. Widen the year window, or show the whole map. Back to the work

Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning

29 cited

2023An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models24 cited

2023Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting21 cited

2022MABEL: Attenuating Gender Bias using Textual Entailment Data20 cited

2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools19 cited

2022Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT17 cited

2023Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models17 cited

2023Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases16 cited

2024Towards fair decision: A novel representation method for debiasing pre-trained models16 cited

2024Travel Demand Forecasting: A Fair AI Approach16 cited

2024Mitigating social biases of pre-trained language models via contrastive self-debiasing with double data augmentation15 cited

2024Measuring complex psychological and sociological constructs in large-scale text2 cited