Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts

TL;DR

This paper presents an agent-based framework utilizing large language models to uncover tacit organizational knowledge through iterative interactions, effectively navigating complex social structures and achieving high knowledge recall.

Contribution

It introduces a novel LLM-driven agent approach for tacit knowledge discovery that does not require direct access to domain experts, enhancing organizational knowledge management.

Findings

Achieves 94.9% full-knowledge recall in simulations

Self-critical feedback correlates with external critic scores

Effectively recovers fragmented knowledge without direct expert access

Abstract

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.