EvalPlus augments HumanEval with 80x more tests via LLM and mutation strategies, exposing up to 28.9% more incorrect LLM-generated code and reversing some model performance rankings.
Leveraging automated unit tests for unsupervised code translation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
CodeT improves code generation accuracy by using the same model to create test cases and then selecting solutions via output agreement on those tests, raising HumanEval pass@1 from 47% to 65.8%.
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
SWaRL trains code LLMs with RL using compiler correctness signals and a confidential verifier reward to embed robust, functionality-preserving watermarks that resist refactoring attacks.
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.
citing papers explorer
-
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
EvalPlus augments HumanEval with 80x more tests via LLM and mutation strategies, exposing up to 28.9% more incorrect LLM-generated code and reversing some model performance rankings.
-
CodeT: Code Generation with Generated Tests
CodeT improves code generation accuracy by using the same model to create test cases and then selecting solutions via output agreement on those tests, raising HumanEval pass@1 from 47% to 65.8%.
-
XSearch: Explainable Code Search via Concept-to-Code Alignment
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
-
LLMs Corrupt Your Documents When You Delegate
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
-
SWaRL: Safeguard Code Watermarking via Reinforcement Learning
SWaRL trains code LLMs with RL using compiler correctness signals and a confidential verifier reward to embed robust, functionality-preserving watermarks that resist refactoring attacks.
-
Boosting Automatic Java-to-Cangjie Translation with Multi-Stage LLM Training and Error Repair
Multi-stage LLM training plus compiler-guided error repair boosts functional equivalence in Java-to-Cangjie translation by 6.06% over prior methods despite scarce parallel data.
- ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories