Papers by Mehrnaz Moslemi
TagDebias: Entity and Concept Tagging for Social Bias Mitigation in Pretrained Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to mitigate social bias in pre-trained language models are limited . researchers have found that these models inherit substantial social biases in their pre-training data . |
| Approach: | They propose a method which proposes debiasing a dataset using type tags and fine-tunes PLMs on this debiased dataset. |
| Outcome: | The proposed method improves bias scores on a ranking task . it is based on analyzing type tags and fine-tuning pre-trained models . |