Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts
This addresses the challenge of capturing fragmented organizational knowledge that is difficult to access through traditional methods, though it appears incremental in applying existing LLM technology to a specific domain problem.
The researchers tackled the problem of documenting tacit knowledge in organizations by developing an agent-based framework using large language models to iteratively reconstruct dataset descriptions through employee interactions, achieving 94.9% full-knowledge recall in simulations across various company structures.
Documenting tacit knowledge in organizations can be a challenging task due to incomplete initial information, difficulty in identifying knowledgeable individuals, the interplay of formal hierarchies and informal networks, and the need to ask the right questions. To address this, we propose an agent-based framework leveraging large language models (LLMs) to iteratively reconstruct dataset descriptions through interactions with employees. Modeling knowledge dissemination as a Susceptible-Infectious (SI) process with waning infectivity, we conduct 864 simulations across various synthetic company structures and different dissemination parameters. Our results show that the agent achieves 94.9% full-knowledge recall, with self-critical feedback scores strongly correlating with external literature critic scores. We analyze how each simulation parameter affects the knowledge retrieval process for the agent. In particular, we find that our approach is able to recover information without needing to access directly the only domain specialist. These findings highlight the agent's ability to navigate organizational complexity and capture fragmented knowledge that would otherwise remain inaccessible.