Citation map · Study

SZodixStudyAcademic Library

Shelves Open access

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

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

16 references·1 citing·38 second hopsampled

FromToDepth

this work references cited by second hop· second hop is a sample of the most-cited connections

References

2019MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations1,413 cited
2018Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science840 cited
2021StereoSet: Measuring stereotypical bias in pretrained language models643 cited
2019On Measuring Social Biases in Sentence Encoders461 cited
2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models438 cited
2019Bias in Bios337 cited
2019Gender Bias in Contextualized Word Embeddings334 cited
2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection286 cited
2020Gender Bias in Neural Natural Language Processing266 cited
2020Towards Debiasing Sentence Representations154 cited
2022Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts119 cited
2022An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models116 cited
2020Measuring and Reducing Gendered Correlations in Pre-trained Models109 cited
2020On Measuring and Mitigating Biased Inferences of Word Embeddings101 cited
2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

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

62 cited

2022Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models58 cited

Cited by

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