Small language models display distinct energy-use and coverage profiles when generating unit tests, with some models being more efficient while others offer higher stability.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Empirical Study of Sustainability in Prompt-driven Test Script Generation Using Small Language Models
Small language models display distinct energy-use and coverage profiles when generating unit tests, with some models being more efficient while others offer higher stability.