AI/ ai · ai-alignment · multilingual-ai

AI Chatbots Answer the Same Moral Question Differently by Language

AI models answer the same moral dilemma differently by language, and a new technique can steer and transfer chosen values across languages.

Ask an AI chatbot the same ethical question in English and Chinese, and you might get two different answers.

Researchers built C-Voices, a dataset of 86,400 dilemma-based prompts across six languages, each pairing an action aligned with Chinese Social Values against a conflicting alternative. The 12 values span national, societal, and personal levels of Chinese culture. Testing several LLMs on identical dilemmas across languages, the team found that value preferences are model-dependent and language-sensitive - the same moral fork in the road produced divergent answers depending on which language it was asked in. To address this, the researchers also built a fine-tuning-free steering method that reads hidden-state differences between value-aligned and value-conflicting responses, then nudges a model's output toward a chosen value during inference.

The practical part is the transfer trick: a value vector extracted in one language can be applied to steer a model's behavior in a different language, without retraining. That means a company could calibrate a model's values once and expect the adjustment to travel across languages, a shortcut that sidesteps the inconsistency the researchers documented in the first place. The method also generalized to two existing value benchmarks, FLAMES and ValuePrism, suggesting the approach isn't just a one-dataset trick.

Translation, it turns out, isn't just a language problem for AI models - it's a values problem too.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →