Adding symbolic-execution-generated tests to APPS improves reward model accuracy for code generation, but barely changes final code-generation quality relative to CodeRL.
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
-
Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
Adding symbolic-execution-generated tests to APPS improves reward model accuracy for code generation, but barely changes final code-generation quality relative to CodeRL.