AI 中文总结
该研究表明，大型语言模型可从专家行为中外部化隐性知识，提升决策质量并帮助新手接近专家表现，为波兰尼悖论提供实证支持，凸显其作为克服专家表述瓶颈的可扩展工具的潜力。
AI 中文摘要
隐性知识，即嵌入经验中的“诀窍”，难以清晰表达，这使得组织中的知识转移成为挑战。隐性知识难以外部化（转化为显性知识），且专业知识往往记录不完善，在专家离职时会流失。本研究探究大型语言模型（LLM）能否从专家的行为中外部化隐性知识，以及此类外部化的知识是否支持下游决策制定和向新手的转移。在两项研究中，我们表明，由LLM外部化的隐性知识可提升决策质量，并使新手能够达到专家级别的表现，其效果常常优于人类专家所表述的知识。这些发现为波兰尼悖论（Polanyi's Paradox）——即我们所知多于所能言——提供了实证支持，并凸显了LLM作为可扩展工具的潜力，可帮助克服人类专家的表述瓶颈。机制分析和稳健性检验显示，LLM能从专家对话中有意义地学习和提取知识，且研究结果在不同模型和检索方法中具有普适性。
英文摘要
Tacit knowledge, or the "know-how" embedded in experience, is difficult to articulate, making its transfer a challenge in organizations. Tacit knowledge is hard to externalize (transform into explicit knowledge), and expertise is often poorly documented and lost when experts leave. This study examines whether LLMs can externalize tacit knowledge from experts' behaviors and whether such externalized knowledge supports downstream decision-making and transfer to novices. Across two studies, we show that LLM-externalized tacit knowledge improves decision quality and enables novices to approach expert-level performance, often outperforming knowledge articulated by human experts. These findings provide empirical support for Polanyi's Paradox -- that we can know more than we can tell -- and highlight the potential of LLMs as scalable tools that can help overcome human experts' articulation bottleneck. Mechanism analyses and robustness checks show that LLMs meaningfully learn and extract knowledge from expert conversations, and findings generalize across models and retrieval methods.
