CODE-DITING distills reasoning from a large reasoning LLM into 1.5B and 7B judges that evaluate generated code without reference solutions or test cases, beating larger judges under majority voting.
Exploring the capabilities of llms for code change related tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation
CODE-DITING distills reasoning from a large reasoning LLM into 1.5B and 7B judges that evaluate generated code without reference solutions or test cases, beating larger judges under majority voting.