Search papers, labs, and topics across Lattice.
The paper investigates redundancy in LLM code generation when using verifier-based reinforcement learning (RLVR) and Pass@k evaluation. It finds that correctness-only RLVR leads to high redundancy in generated code implementations, hindering performance at larger sampling budgets. To mitigate this, the authors introduce an anti-redundancy reward based on JPlag similarity within the RLVR framework, demonstrating improved executable performance across multiple models and benchmarks.
Naive RL fine-tuning for code generation can lead to LLMs regurgitating the same solutions, but penalizing code similarity boosts performance even more than directly optimizing for pass@k.
LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite sampling budget. While recent verifier-based reinforcement learning (RLVR) methods improve executable correctness, how these objectives affect redundancy among sampled programs remains poorly understood. In this work, we study implementation-level redundancy in code generation using JPlag, a plagiarism-detection system for code. Across models and benchmarks, we show that correctness-only RLVR often concentrates generations around repeated implementations, whereas Pass@k-aware objectives maintain lower redundancy and improve larger-budget performance. Motivated by these observations, we augment RLVR with direct anti-redundancy rewards based on JPlag similarity. Across 3 models and 3 benchmarks, discouraging near-duplicate generations reliably improves finite-budget executable performance, often matching or outperforming specialized Pass@k-aware objectives.
