Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value

Jing Yao, Xiaoyuan Yi, Yifan Gong, Xiting Wang, Xing Xie


Abstract
Value alignment is crucial for the responsible development of Large Language Models (LLMs). However, how to define values in this context remains largely unexplored. Existing work mainly specifies values as risk criteria formulated in the AI community, e.g., fairness and privacy protection, suffering from poor clarity, adaptability and transparency. Leveraging basic values established in humanity and social science that are compatible with values across cultures, this paper introduces a novel value space spanned by multiple basic value dimensions and proposes BaseAlign, a corresponding value alignment paradigm. Applying the representative Schwartz’s Theory of Basic Values as an instantiation, we construct FULCRA, a dataset consisting of 20k (LLM output, value vector) pairs. LLMs’ outputs are mapped into the K-dim value space beyond simple binary labels, by identifying their underlying priorities for these value dimensions. Extensive analysis and experiments on FULCRA: (1) reveal the essential relation between basic values and LLMs’ behaviors, (2) demonstrate that our paradigm with basic values not only covers existing risks but also anticipates the unidentified ones, and (3) manifest BaseAlign’s superiority in alignment performance with less data, paving the way for addressing the above three challenges.
Anthology ID:
2024.naacl-long.486
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:
8762–8785
Language:
URL:
https://aclanthology.org/2024.naacl-long.486
DOI:
10.18653/v1/2024.naacl-long.486
Bibkey:
Cite (ACL):
Jing Yao, Xiaoyuan Yi, Yifan Gong, Xiting Wang, and Xing Xie. 2024. Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value. 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 8762–8785, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value (Yao et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.486.pdf