Recent advancements in Large Language Models (LLMs) have heightened concerns about their potential misalignment with human values. However, evaluating their grasp of these values is complex due to their intricate and adaptable nature. We argue that truly understanding values in LLMs requires considering both "know what" and "know why". To this end, we present the Value Understanding Measurement (VUM) framework that quantitatively assess both "know what" and "know why" by measuring the discriminator-critique gap related to human values. Using the Schwartz Value Survey, we specify our evaluation values and develop a thousand-level dialogue dataset with GPT-4. Our assessment looks at both the value alignment of LLM's outputs compared to baseline answers and how LLM responses align with reasons for value recognition versus GPT-4's annotations. We evaluate five representative LLMs and provide strong evidence that the scaling law significantly impacts "know what" but not much on "know why", which has consistently maintained a high level. This may further suggest that LLMs might craft plausible explanations based on the provided context without truly understanding their inherent value, indicating potential risks.

翻译：近期大型语言模型（LLMs）的进步加剧了人们对其与人类价值观潜在错位的担忧。然而，由于价值观复杂且具有适应性的本质，评估LLMs对价值观的理解颇具挑战性。我们认为，真正理解LLM中的价值观需要同时考虑"知其然"与"知其所以然"。为此，我们提出价值理解测量（VUM）框架，通过测量与人类价值观相关的判别器-批评差距，定量评估"知其然"与"知其所以然"。借助施瓦茨价值观调查，我们明确了评估价值观体系，并利用GPT-4开发了包含千层级对话的数据集。评估既考察LLM输出与基线答案的价值对齐程度，也分析LLM响应与GPT-4标注中价值识别理由的对齐情况。我们对五个代表性LLM的评估提供了有力证据：规模法则显著影响"知其然"能力，但对始终维持高水平的"知其所以然"影响有限。这进一步表明，LLMs可能基于给定上下文构建看似合理的解释，却未真正理解其内在价值观，揭示了潜在风险。