Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
Abstract: Prior research has revealed that abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual context, with a specific focus on human values-related concepts (i.e., value concepts) due to their significance for AI safety. Through our comprehensive exploration covering 7 types of human values, 16 languages and 3 LLM series with distinct multilinguality, we first empirically confirm the presence of value concepts within LLMs in a multilingual format. Further analysis on the cross-lingual characteristics of these concepts reveals 3 traits arising from language resource disparities: cross-lingual inconsistency, distorted linguistic relationships, and unidirectional cross-lingual transfer between high- and low-resource languages, all in terms of value concepts. Moreover, we validate the feasibility of cross-lingual control over value alignment capabilities of LLMs, leveraging the dominant language as a source language. Ultimately, recognizing the significant impact of LLMs' multilinguality on our results, we consolidate our findings and provide prudent suggestions on the composition of multilingual data for LLMs pre-training.
Paper Type: Long
Research Area: Multilingualism and Cross-Lingual NLP
Research Area Keywords: Multilingualism and Cross-Lingual NLP
Contribution Types: Model analysis & interpretability
Languages Studied: English,Chinese,Catalan,French,Indonesian,Portuguese,Spanish,Chichewa,Swahili,Tamil,Telugu,Finnish,Hungarian,Japanese,Korean,Vietnamese
Submission Number: 572
Loading