Execution-based selectors for LLM code candidates outperform textual voting by large margins across configurations, with input generation quality mattering more than the specific aggregation rule.
Findings of the Association for Computational Linguistics: ACL 2025 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
Execution-based selectors for LLM code candidates outperform textual voting by large margins across configurations, with input generation quality mattering more than the specific aggregation rule.