机器性格的更好天使：性格如何与LLM安全性相关
The Better Angels of Machine Personality: How Personality Relates to LLM Safety
AI总结：
本文基于MBTI-M量表发现LLM性格特质与安全能力相关，通过编辑性格（如ISTJ至ISTP）可显著提升隐私和公平性能，并揭示不同性格对越狱攻击的差异敏感性，为LLM安全增强提供新视角。
摘要：
性格心理学家已经分析了人类社会中性格与安全行为之间的关系。尽管大型语言模型（LLMs）展现出性格特质，但LLMs中性格特质与安全能力之间的关系仍然是一个谜。在本文中，我们基于可靠的MBTI-M量表发现，LLMs的性格特质与其安全能力（即毒性、隐私和公平性）密切相关。同时，安全对齐通常会增加各种LLMs的外向性、感觉和判断特质。根据这些发现，我们可以编辑LLMs的性格特质并提高其安全性能，例如，将性格从ISTJ诱导为ISTP，隐私和公平性能分别相对提高了约43%和10%。此外，我们发现具有不同性格特质的LLMs对越狱攻击的 susceptibility 不同。这项研究开创了从性格角度研究LLM安全性的先河，为增强LLM安全性提供了新的见解。
英文摘要：
Personality psychologists have analyzed the relationship between personality and safety behaviors in human society. Although Large Language Models (LLMs) demonstrate personality traits, the relationship between personality traits and safety abilities in LLMs still remains a mystery. In this paper, we discover that LLMs' personality traits are closely related to their safety abilities, i.e., toxicity, privacy, and fairness, based on the reliable MBTI-M scale. Meanwhile, the safety alignment generally increases various LLMs' Extraversion, Sensing, and Judging traits. According to such findings, we can edit LLMs' personality traits and improve their safety performance, e.g., inducing personality from ISTJ to ISTP resulted in a relative improvement of approximately 43% and 10% in privacy and fairness performance, respectively. Additionally, we find that LLMs with different personality traits are differentially susceptible to jailbreak. This study pioneers the investigation of LLM safety from a personality perspective, providing new insights into LLM safety enhancement.
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。
