MMODELYST
Papers/Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs
PAP

Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs

May 21, 2026

arXiv
Abstract

Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LLMs) can infer individual domain knowledge directly from long-term Slack logs. Analyzing 27,188 messages from 43 users, we evaluated seven models (including Gemini, Claude, and GPT families) by comparing their zero-shot estimates against self-reported skill ratings from 27 participants. Gemini 2.5 Flash achieved the lowest error (MAE 21.13%), while GPT models showed significantly larger discrepancies. Notably, estimation accuracy depended only weakly on message volume, indicating that more text alone does not guarantee better inference. These findings demonstrate the feasibility and current limits of automated expertise mapping, highlighting the need for privacy-preserving deployments and richer, structure-aware representations of human knowledge.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Ko Watanabe, Shoya Ishimaru
Your notes (browser-local)
saved
arXiv:2605.22971