LLMs achieve highest dialogue annotation accuracy via multi-agent prompting but show context-dependent performance and directional biases, with better results in K-12 affective coding and systematic errors in cognitive and behavioral categories.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decoding Student Dialogue: A Multi-Dimensional Comparison and Bias Analysis of Large Language Models as Annotation Tools
LLMs achieve highest dialogue annotation accuracy via multi-agent prompting but show context-dependent performance and directional biases, with better results in K-12 affective coding and systematic errors in cognitive and behavioral categories.