REAG and a confidence-calibrated cascade generate context-aware test oracles for LLM-based software and produce statistically controlled verdict reliability, demonstrated on a production nutrition advisory app.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Requirements-Augmented Generation for Trustworthy Acceptance Testing of LLM-Based Software
REAG and a confidence-calibrated cascade generate context-aware test oracles for LLM-based software and produce statistically controlled verdict reliability, demonstrated on a production nutrition advisory app.