ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917776056123392 |
|---|---|
| author | Han, Pengrui Kocielnik, Rafal Saravanan, Adhithya Jiang, Roy Sharir, Or Anandkumar, Anima |
| author_facet | Han, Pengrui Kocielnik, Rafal Saravanan, Adhithya Jiang, Roy Sharir, Or Anandkumar, Anima |
| contents | Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data, aiming to enhance the debiasing of LLMs. We propose two strategies: Targeted Prompting, which provides effective debiasing for known biases but necessitates prior specification of bias in question; and General Prompting, which, while slightly less effective, offers debiasing across various categories. We leverage resource-efficient LLM debiasing using adapter tuning and compare the effectiveness of our synthetic data to existing debiasing datasets. Our results reveal that: (1) ChatGPT can efficiently produce high-quality training data for debiasing other LLMs; (2) data produced via our approach surpasses existing datasets in debiasing performance while also preserving internal knowledge of a pre-trained LLM; and (3) synthetic data exhibits generalizability across categories, effectively mitigating various biases, including intersectional ones. These findings underscore the potential of synthetic data in advancing the fairness of LLMs with minimal retraining cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11764 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs Han, Pengrui Kocielnik, Rafal Saravanan, Adhithya Jiang, Roy Sharir, Or Anandkumar, Anima Computation and Language Artificial Intelligence Computers and Society 68T50 I.2.7; K.4.1 Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data, aiming to enhance the debiasing of LLMs. We propose two strategies: Targeted Prompting, which provides effective debiasing for known biases but necessitates prior specification of bias in question; and General Prompting, which, while slightly less effective, offers debiasing across various categories. We leverage resource-efficient LLM debiasing using adapter tuning and compare the effectiveness of our synthetic data to existing debiasing datasets. Our results reveal that: (1) ChatGPT can efficiently produce high-quality training data for debiasing other LLMs; (2) data produced via our approach surpasses existing datasets in debiasing performance while also preserving internal knowledge of a pre-trained LLM; and (3) synthetic data exhibits generalizability across categories, effectively mitigating various biases, including intersectional ones. These findings underscore the potential of synthetic data in advancing the fairness of LLMs with minimal retraining cost. |
| title | ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs |
| topic | Computation and Language Artificial Intelligence Computers and Society 68T50 I.2.7; K.4.1 |
| url | https://arxiv.org/abs/2402.11764 |