An LLM-based specification-alignment method that lifts the model's perceived requirements from generated code and applies ten alignment rules improves Pass@1 by about 30% over existing baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aligning Requirement for Large Language Model's Code Generation
An LLM-based specification-alignment method that lifts the model's perceived requirements from generated code and applies ten alignment rules improves Pass@1 by about 30% over existing baselines.