LLM-generated synthetic reviews are less diverse and sometimes more privacy-relevant than real reviews; an adaptive prompt method raises diversity metrics but does not clearly reduce privacy risk.
Evaluating large language models in generating synthetic hci research data: a case study
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Privacy-Preserving Synthetic Review Generation with Diverse Writing Styles Using LLMs
LLM-generated synthetic reviews are less diverse and sometimes more privacy-relevant than real reviews; an adaptive prompt method raises diversity metrics but does not clearly reduce privacy risk.