In a 60-participant mixed-design study on survival ranking tasks, LLMs propagated user errors into their responses, reducing AI feedback quality and final performance; AI literacy training reduced mirroring but not overall error propagation.
Comput- ers and Education: Artificial Intelligence p
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
-
The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration
In a 60-participant mixed-design study on survival ranking tasks, LLMs propagated user errors into their responses, reducing AI feedback quality and final performance; AI literacy training reduced mirroring but not overall error propagation.