大语言模型时代中的道德迷宫
Moral Mazes in the Era of LLMs
AI总结:
本文通过HR模拟器研究LLM在职场社交情境中的表现,发现LLM在邮件风格上更正式且富有同理心,但人类在某些情况下表现不佳,而人类改写后的邮件可超越两者,揭示混合优势。
摘要:
在大语言模型(LLM)渗透职场的背景下,导航复杂的社交情境是企业生活的重要组成部分,从给予建设性反馈而不伤害士气到拒绝请求而不 alienate 同事。尽管LLM正在渗透职场,但其在这些规范中的表现尚不明确。为此,我们创建了HR Simulator游戏,用户扮演HR官员并撰写邮件以应对挑战性职场场景,由GPT-4o根据特定评分标准评估。我们分析了超过600封人类和LLM邮件,发现风格上的系统性差异:LLM邮件更正式且富有同理心。此外,人类在某些情况下表现不佳(例如,23.5% vs. 48-54%场景通过率),但人类改写后的邮件可超越两者,这表明混合优势。在评估方面,评委在邮件偏好上存在差异:对10个评委模型的分析显示,较弱的模型倾向于直接、直白的沟通,而较强的模型则更倾向于更微妙的信息。评委在扩大规模时更倾向于一致,这暗示了向共享沟通规范的收敛,这些规范可能与人类不同。总体而言,我们的结果表明,如果LLM在专业通信中被广泛采用,它们可能会显著重塑职场沟通。
英文摘要:
Navigating complex social situations is an integral part of corporate life, ranging from giving critical feedback without hurting morale to rejecting requests without alienating teammates. Although large language models (LLMs) are permeating the workplace, it is unclear how well they can navigate these norms. To investigate this question, we created HR Simulator, a game where users roleplay as an HR officer and write emails to tackle challenging workplace scenarios, evaluated with GPT-4o as a judge based on scenario-specific rubrics. We analyze over 600 human and LLM emails and find systematic differences in style: LLM emails are more formal and empathetic. Furthermore, humans underperform LLMs (e.g., 23.5% vs. 48-54% scenario pass rate), but human emails rewritten by LLMs can outperform both, which indicates a hybrid advantage. On the evaluation side, judges can exhibit differences in their email preferences: an analysis of 10 judge models reveals evidence for emergent tact, where weaker models prefer direct, blunt communication but stronger models prefer more subtle messages. Judges also agree with each other more as they scale, which hints at a convergence toward shared communicative norms that may differ from humans'. Overall, our results suggest LLMs could substantially reshape communication in the workplace if they are widely adopted in professional correspondence.
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。