RPG penalizes tokens that continue repeated grammar structures in LLM-generated code, reducing structural repetition and improving Pass@k on HumanEval and MBPP.
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
-
Rethinking Repetition Problems of LLMs in Code Generation
RPG penalizes tokens that continue repeated grammar structures in LLM-generated code, reducing structural repetition and improving Pass@k on HumanEval and MBPP.