GPT-4o-generated follow-up questions are rated equal to human questions when minimally guided, and better when guided by a 14-type interviewer mistake framework.
Can LLMs replace man- ual annotation of software engineering artifacts?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Requirements Elicitation Follow-Up Question Generation
GPT-4o-generated follow-up questions are rated equal to human questions when minimally guided, and better when guided by a 14-type interviewer mistake framework.