3 papers
cs.SE2026
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
Kaifeng He, Xiaojun Zhang, Peiliang Cai +7
Large language models (LLMs) frequently generate defective outputs in code generation tasks, ranging from logical bugs to security vulnerabilities. While these generation failures…
cs.SE2026
AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation
Kaifeng He, Mingwei Liu, Chong Wang +4
Code generation with large language models (LLMs) is highly sensitive to token selection during decoding, particularly at uncertain decision points that influence program logic. Wh…
cs.SE2025
A Preliminary Study on the Robustness of Code Generation by Large Language Models
Zike Li, Mingwei Liu, Anji Li +4
Robustness is a critical factor for reliable code generation by large language models, yet most evaluations focus on correctness and overlook key issues such as missing input valid…