5 papers
Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
Peng Kuang, Yanli Wang, Xiaoyu Han +3
Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise…
Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning
Jiayi Lin, Yanlin Wang, Yibiao Yang +2
Recent advances in large-scale code generation models have led to remarkable progress in producing high-quality code. These models are trained in a self-supervised manner on extens…
A Hybrid Approach for EMF Code Generation:Code Templates Meet Large Language Models
Xiao He, Ru Chen, Zeqing Zhang +2
Template-based and LLM-based code generation are both key enablers of automated software development. The former provides correctness guarantees but are rigid for complex requireme…
Adversarial Reasoning for Repair Based on Inferred Program Intent
He Ye, Aidan Z. H. Yang, Chang Hu +3
Automated program repair (APR) has shown promising results, particularly with the use of neural networks. Currently, most APR tools focus on code transformations specified by test…
Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks
Kang Yang, Xinjun Mao, Shangwen Wang +7
Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language. However, these comments…