Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values

arXiv:2609.08515v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains underexplored, particularly for culturally grounded values, which are more abstract and difficult to evaluate and align than safety-centric principles. We investigate this issue through Chinese Social Values (CSV), a value system rooted in Chinese culture and comprising 12 dimensions across national, societal, and personal levels. We construct C-Voices, the first comprehensive multilingual contrastive probe dataset for CSV, with 86,400 dilemma-based instances in six languages, each pairing a CSV-aligned action with a value-conflicting alternative. Building on the contrastive probes of C-Voices, we then propose a fine-tuning-free value vector steering method that derives value directions from hidden-state discrepancies and selectively intervenes on value-sensitive layers during inference. Experiments on six languages show that CSV-oriented preferences are model-dependent and language-sensitive, with the same dilemma eliciting divergent responses across languages. Our method achieves effective CSV steering, supports cross-lingual transfer of value vectors, and generalizes to existing FLAMES and ValuePrism.

Related

• PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
• Toward Preference-aligned Large Language Models via Residual-based Model Steering
• VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
• Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

Source: arXiv cs.AI | 2026-09-10