New 600-pair verified NL2SH test set and an execution-plus-LLM equivalence checker improve Bash-command translation evaluation; parsing and in-context learning give the largest gains for small models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM-Supported Natural Language to Bash Translation
New 600-pair verified NL2SH test set and an execution-plus-LLM equivalence checker improve Bash-command translation evaluation; parsing and in-context learning give the largest gains for small models.