LLMs can infer individual domain knowledge from Slack logs with best MAE of 21.13% using Gemini 2.5 Flash, though performance varies by model and shows weak dependence on message volume.
Association for Computing Machinery, New York, NY, USA, 313–316
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An LLM acting as a teachable student for vocabulary learning by teaching produced better retention than traditional methods in a 10-person study at 3- and 7-day follow-ups.
citing papers explorer
-
Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs
LLMs can infer individual domain knowledge from Slack logs with best MAE of 21.13% using Gemini 2.5 Flash, though performance varies by model and shows weak dependence on message volume.
-
Empowering Vocabulary Learning Through Teaching AI: Using LLMs as a Student to Perform Learning by Teaching in Vocabulary Acquisition
An LLM acting as a teachable student for vocabulary learning by teaching produced better retention than traditional methods in a 10-person study at 3- and 7-day follow-ups.