arXivAI Research
Evaluating LLMs Without Ground Truth: Lessons from Stated-Preference Economics
當沒有標準答案時：如何用「陳述偏好經濟學」評估大型語言模型
This paper introduces a 'stated-preference' economics framework to evaluate LLMs on subjective questions without ground-truth answers, testing their internal coherence and theoretical validity.
2 min read