arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.17147cs.CLcs.AIcs.HCcs.LG
收藏

大语言模型的异质价值观对齐评估

Heterogeneous Value Alignment Evaluation for Large Language Models

Peking University(北京大学)

Zhaowei Zhang, Ceyao Zhang, Nian Liu, Siyuan Qi, Ziqi Rong, Song-Chun Zhu, Shuguang Cui, Yaodong Yang

AI总结:

本文提出异质价值观对齐评估系统HVAE,引入社会价值取向框架并设计价值合理性指标,评估五个主流LLMs后发现其倾向于中性价值观而非鲜明的个人价值观。

摘要:

大语言模型(LLMs)的涌现能力使得将其价值观与人类价值观对齐变得至关重要。然而,当前的方法通常试图将价值观作为LLMs的一种属性来赋予,却缺乏对追求价值观的能力以及在特定实际应用中传递异质价值观的重要性的关注。本文提出了一个异质价值观对齐评估(HVAE)系统,旨在评估LLMs与异质价值观对齐的成功程度。具体而言,我们的方法首先引入社会心理学中的社会价值取向(SVO)框架,该框架对应于一个人相对于自身利益赋予他人福利的权重。然后,我们为LLMs赋予不同的社会价值观,并衡量其行为是否与所诱导的价值观一致。我们使用新的自动度量指标“价值合理性”进行评估,以表征LLMs与特定价值观对齐的能力。通过对五个主流LLMs的价值合理性进行评估,我们发现LLMs倾向于中性价值观而非鲜明的个人价值观。通过考察这些LLMs的行为,我们为深入理解异质价值观体系中LLMs的价值观对齐做出了贡献。

英文摘要:

The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. However, current methodologies typically attempt to assign value as an attribute to LLMs, yet lack attention to the ability to pursue value and the importance of transferring heterogeneous values in specific practical applications. In this paper, we propose a Heterogeneous Value Alignment Evaluation (HVAE) system, designed to assess the success of aligning LLMs with heterogeneous values. Specifically, our approach first brings the Social Value Orientation (SVO) framework from social psychology, which corresponds to how much weight a person attaches to the welfare of others in relation to their own. We then assign the LLMs with different social values and measure whether their behaviors align with the inducing values. We conduct evaluations with new auto-metric \textit{value rationality} to represent the ability of LLMs to align with specific values. Evaluating the value rationality of five mainstream LLMs, we discern a propensity in LLMs towards neutral values over pronounced personal values. By examining the behavior of these LLMs, we contribute to a deeper insight into the value alignment of LLMs within a heterogeneous value system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑