Paper Number
ICIS2026-4098
Paper Type
Completed
Abstract
Capturing tacit knowledge, or the “know-how” embedded in individual experiences and contexts, is a central challenge that limits the preservation and transfer of valuable expertise. Here, we show that Large Language Models (LLMs) can uncover tacit knowledge from expert behavior and support knowledge transfer from experts to novices. We first identify prompting strategies that improve LLMs' ability to externalize tacit knowledge (i.e., transform tacit into explicit knowledge), and then evaluate the downstream utility of the resulting LLM-externalized tacit knowledge. Our analysis reveals that LLM-externalized tacit knowledge incorporating expert behavior improves decision quality and enables novices to approach expert-level performance, 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 suggest that LLMs can help overcome human experts’ articulation bottleneck that has long challenged tacit knowledge externalization.
Recommended Citation
Cho, Mina; Funk, Russell; Gupta, Alok; and Yang, Mochen, "Large Language Models Can Explain Experts Better Than Experts Themselves" (2026). ICIS 2026 Proceedings. 9.
https://aisel.aisnet.org/icis2026/gentopics/gentopics/9
Large Language Models Can Explain Experts Better Than Experts Themselves
Capturing tacit knowledge, or the “know-how” embedded in individual experiences and contexts, is a central challenge that limits the preservation and transfer of valuable expertise. Here, we show that Large Language Models (LLMs) can uncover tacit knowledge from expert behavior and support knowledge transfer from experts to novices. We first identify prompting strategies that improve LLMs' ability to externalize tacit knowledge (i.e., transform tacit into explicit knowledge), and then evaluate the downstream utility of the resulting LLM-externalized tacit knowledge. Our analysis reveals that LLM-externalized tacit knowledge incorporating expert behavior improves decision quality and enables novices to approach expert-level performance, 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 suggest that LLMs can help overcome human experts’ articulation bottleneck that has long challenged tacit knowledge externalization.
Comments
02_General_topics