Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve their versatile capabilities, including their ability to solve language tasks and equitably represent various genders. To address this issue, we introduce a streamlined Dual Dabiasing Algorithm through Model Adaptation (2DAMA). Novel Dual Debiasing enables robust reduction of stereotypical bias while preserving desired factual gender information encoded by language models. We show that 2DAMA effectively reduces gender bias in English and is one of the first approaches facilitating the mitigation of stereotypical tendencies in translation. The proposed method's key advantage is the preservation of factual gender cues, which are useful in a wide range of natural language processing tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address the…
Counterfactual Debiasing Inference for Compositional Action Recognition
Compositional action recognition is a novel challenge in the computer vision community and focuses on revealing the different combinations of verbs and nouns instead of treating subject-object interactions in videos as i…
Action RecognitionCausal InferencecounterfactualCounterfactual InferenceSustainable Modular Debiasing of Language Models
Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technolo…
FairnessLanguage ModelingLanguage ModellingTextual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation
Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identi…
Data AugmentationBias DetectionSocial-Group-Agnostic Word Embedding Debiasing via the Stereotype Content Model
Existing word embedding debiasing methods require social-group-specific word pairs (e.g., "man"-"woman") for each social attribute (e.g., gender), which cannot be used to mitigate bias for other social groups, making the…
Attribute