LLM-Assisted Content Conditional Debiasing for Fair Text Embedding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914846112481280 |
|---|---|
| author | Deng, Wenlong Chen, Blair Zhao, Beidi Zhang, Chiyu Li, Xiaoxiao Thrampoulidis, Christos |
| author_facet | Deng, Wenlong Chen, Blair Zhao, Beidi Zhang, Chiyu Li, Xiaoxiao Thrampoulidis, Christos |
| contents | Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search engines. In response, this paper proposes a novel method for learning fair text embeddings. First, we define a novel content-conditional equal distance (CCED) fairness for text embeddings, ensuring content-conditional independence between sensitive attributes and text embeddings. Building on CCED, we introduce a content-conditional debiasing (CCD) loss to ensure that embeddings of texts with different sensitive attributes but identical content maintain the same distance from the embedding of their corresponding neutral text. Additionally, we tackle the issue of insufficient training data by using Large Language Models (LLMs) with instructions to fairly augment texts into different sensitive groups. Our extensive evaluations show that our approach effectively enhances fairness while maintaining the utility of embeddings. Furthermore, our augmented dataset, combined with the CCED metric, serves as an new benchmark for evaluating fairness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14208 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM-Assisted Content Conditional Debiasing for Fair Text Embedding Deng, Wenlong Chen, Blair Zhao, Beidi Zhang, Chiyu Li, Xiaoxiao Thrampoulidis, Christos Computation and Language Artificial Intelligence Computers and Society Machine Learning Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search engines. In response, this paper proposes a novel method for learning fair text embeddings. First, we define a novel content-conditional equal distance (CCED) fairness for text embeddings, ensuring content-conditional independence between sensitive attributes and text embeddings. Building on CCED, we introduce a content-conditional debiasing (CCD) loss to ensure that embeddings of texts with different sensitive attributes but identical content maintain the same distance from the embedding of their corresponding neutral text. Additionally, we tackle the issue of insufficient training data by using Large Language Models (LLMs) with instructions to fairly augment texts into different sensitive groups. Our extensive evaluations show that our approach effectively enhances fairness while maintaining the utility of embeddings. Furthermore, our augmented dataset, combined with the CCED metric, serves as an new benchmark for evaluating fairness. |
| title | LLM-Assisted Content Conditional Debiasing for Fair Text Embedding |
| topic | Computation and Language Artificial Intelligence Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2402.14208 |