TestAgent uses a large language model to make adaptive tests conversational, reporting modest accuracy gains and a 20 percent question reduction, but mainly on GPT-4-simulated data.
InPro- ceedings of the AAAI Conference on Artificial Intelli- gence, volume 38, pages 19368–19376
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
TestAgent: An Adaptive and Intelligent Expert for Human Assessment
TestAgent uses a large language model to make adaptive tests conversational, reporting modest accuracy gains and a 20 percent question reduction, but mainly on GPT-4-simulated data.