Nothing Special   »   [go: up one dir, main page]

IterAlign: Iterative Constitutional Alignment of Large Language Models

Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, Wei Wang


Abstract
With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional AI (CAI) have been proposed for LLM alignment. However, these methods require either heavy human annotations or explicitly pre-defined constitutions, which are labor-intensive and resource-consuming. To overcome these drawbacks, we study constitution-based LLM alignment and propose a data-driven constitution discovery and self-alignment framework called IterAlign. IterAlign leverages red teaming to unveil the weaknesses of an LLM and automatically discovers new constitutions using a stronger LLM. These constitutions are then used to guide self-correction of the base LLM. Such a constitution discovery pipeline can be run iteratively and automatically to discover new constitutions that specifically target the alignment gaps in the current LLM. Empirical results on several safety benchmark datasets and multiple base LLMs show that IterAlign successfully improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness.
Anthology ID:
2024.naacl-long.78
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1423–1433
Language:
URL:
https://aclanthology.org/2024.naacl-long.78
DOI:
10.18653/v1/2024.naacl-long.78
Bibkey:
Cite (ACL):
Xiusi Chen, Hongzhi Wen, Sreyashi Nag, Chen Luo, Qingyu Yin, Ruirui Li, Zheng Li, and Wei Wang. 2024. IterAlign: Iterative Constitutional Alignment of Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1423–1433, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
IterAlign: Iterative Constitutional Alignment of Large Language Models (Chen et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.78.pdf