SkelDPO improves code generation efficiency by 2-7% over prior DPO methods via joint preference losses on full code and efficiency-critical skeletons.
Bigo (bench)--can llms generate code with controlled time and space complexity?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Extrapolative weight averaging of RL checkpoints trained under nested unit-test coverage extends a correctness-efficiency frontier and boosts ensemble pass rates in code generation across model scales and inference modes.
EffiSkel improves LLM-generated code efficiency by supervising on extracted structural efficiency skeletons via multi-task learning of code generation and skeleton prediction.
CodeGolf Bench is a dynamic benchmark for LLM concise code generation in 60 languages, showing reasoning models reach 70.97% average human percentile on Python and C++ tasks while non-reasoning models lag.
citing papers explorer
-
SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation
SkelDPO improves code generation efficiency by 2-7% over prior DPO methods via joint preference losses on full code and efficiency-critical skeletons.
-
Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
Extrapolative weight averaging of RL checkpoints trained under nested unit-test coverage extends a correctness-efficiency frontier and boosts ensemble pass rates in code generation across model scales and inference modes.
-
Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation
EffiSkel improves LLM-generated code efficiency by supervising on extracted structural efficiency skeletons via multi-task learning of code generation and skeleton prediction.
-
CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models
CodeGolf Bench is a dynamic benchmark for LLM concise code generation in 60 languages, showing reasoning models reach 70.97% average human percentile on Python and C++ tasks while non-reasoning models lag.
- MetaLint: Easy-to-Hard Generalization for Code Linting