GPT-4o with simple boundary prompts catches some injected faults in small C programs, but it does not consistently beat random testing, MLBVA, or Klee, and the boundary prompts are not verified to produce boundary values.
Analysis and testing using boundary value analysis methods for geographic information system,
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.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Boundary Value Test Input Generation Using Prompt Engineering with LLMs: Fault Detection and Coverage Analysis
GPT-4o with simple boundary prompts catches some injected faults in small C programs, but it does not consistently beat random testing, MLBVA, or Klee, and the boundary prompts are not verified to produce boundary values.