Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version 事件

Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version arXiv:2606.11399v1 Announce Type: new Abstract: Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cultural alignment typically rely on direct prompting with survey-style questions, which frequently elicit neutral or safety-aligned responses and fail to capture underlying model preferences. We propose a f