Verification-guided fine-tuning with mutants and refinement traces teaches CodeLLMs to emit intermediate executable assertions that improve checking and repair on HumanExec.
Inferring better contracts,
1 Pith paper cite this work, alongside 98 external citations. Polarity classification is still indexing.
1
Pith paper citing it
98
external citations · external index
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Teaching Code LLMs to Reason with Intermediate Formal Specifications
Verification-guided fine-tuning with mutants and refinement traces teaches CodeLLMs to emit intermediate executable assertions that improve checking and repair on HumanExec.