Larger batch sizes for LLM dialogue coding in healthcare simulations improve speed and reduce energy consumption while decreasing coding accuracy compared to human labels.
MIT Press, Cambridge, MA (2006)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Semester-long tracking of 96 students showed LLM usage fell 42.7 points and verification dropped 19.4 points in team work, with 18.9% of consistent individual users stopping entirely in teams.
citing papers explorer
-
Less Deliberate in Teams: Student LLM Use Across Individual and Collaborative Work
Semester-long tracking of 96 students showed LLM usage fell 42.7 points and verification dropped 19.4 points in team work, with 18.9% of consistent individual users stopping entirely in teams.