6 papers
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
Lingxiao Tang, He Ye, Zhaoyang Chu +4
Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, pri…
Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
Kerui Huang, Shuhan Liu, Xing Hu +3
Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense task…
FGIT: Fault-Guided Fine-Tuning for Code Generation
Lishui Fan, Zhongxin Liu, Haoye Wang +3
Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) so…
Code2API: A Tool for Generating Reusable APIs from Stack Overflow Code Snippets
Yubo Mai, Zhipeng Gao, Xing Hu +3
Nowadays, developers often turn to Stack Overflow for solutions to daily problems, however, these code snippets are partial code that cannot be tested and verified properly. One wa…
LLM4SZZ: Enhancing SZZ Algorithm with Context-Enhanced Assessment on Large Language Models
Lingxiao Tang, Jiakun Liu, Zhongxin Liu +2
The SZZ algorithm is the dominant technique for identifying bug-inducing commits and serves as a foundation for many software engineering studies, such as bug prediction and static…
Automating Comment Generation for Smart Contract from Bytecode
Jianhang Xiang, Zhipeng Gao, Lingfeng Bao +3
Recently, smart contracts have played a vital role in automatic financial and business transactions. To help end users without programming background to better understand the logic…