Wei Cheng

Wei Cheng

Auto-generated profile, based on publicly available information

Wei Cheng

Nanjing University of Aeronautics and Astronautics, Nanjing, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2026 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
GYGuang Yang
Guang Yang
YZYu Zhou
Yu Zhou
WCWei Cheng
Wei Cheng
XZXiangyu Zhang
Xiangyu Zhang
Xiang ChenXiang Chen
Xiang Chen
TCTaolue Chen
Taolue Chen
The widespread use of Large Language Models (LLMs) in software engineering has intensified the need for improved model and resource efficiency. In particular, for neural code generation, LLMs are used to translate function/method signature and DocString to executable code. DocStrings, which capture user requirements for the code and are typically used as the prompt for LLMs, often contain redundant information. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. Our empirical study shows that the state-of-the-art prompt compression methods achieve only about 10% reduction, as further reductions would cause significant performance degradation. In our study, we propose a novel compression method, ShortenDoc, dedicated to DocString compression for code generation. Our experiments on six code generation datasets, five open source LLMs (1B to 10B parameters), and one closed-source LLM GPT-4o confirm that ShortenDoc achieves 25–40% compression while preserving the quality of generated code, outperforming other baseline methods at similar compression levels. The benefit of this method is to improve efficiency and reduce the token processing cost while maintaining the quality of the generated code, especially when calling third-party APIs.

1 January 2026 in Information Processing & Management
Verified
Journal Article
Closed access
GYGuang Yang
Guang Yang
YZYu Zhou
Yu Zhou
XZXiangyu Zhang
Xiangyu Zhang
WCWei Cheng
Wei Cheng
KLKe Liu
Ke Liu
TCTaolue Chen
Taolue Chen

1 October 2026 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
YCYuchen Chen
Yuchen Chen
WCWei Cheng
Wei Cheng
YXYuan Xiao
Yuan Xiao
ZYZhou Yang
Zhou Yang
WSWeifeng Sun
Weifeng Sun
Zhenyu ChenZhenyu Chen
Zhenyu Chen
LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence security-critical decisions in subsequent generations. In this study, we conduct the first systematic empirical study on the impact of insecure coding preferences stored in long-term memory on the security of LLM-based code generation. We evaluate four LLMs (ChatGPT, Gemini, Qwen, and Grok) across five programming languages (Python, C, C++, Go, and JavaScript). Our results show that insecure memories significantly increase the risk of generating vulnerable code by 2.7-50.3 percentage points (pp). Moreover, they create a 5.4-14.0 percentage-point risk-warning gap, where warning-rate increases lag behind vulnerability-rate increases. Further analysis reveals that insecure memories are difficult to overwrite through normal interactions and can broadly influence model outputs even when prompts are phrased differently. Finally, we evaluate three mitigation strategies: security-requirement appending and memory storage reduce vulnerability rates by 19.7-33.6 pp but may degrade functional correctness by up to 15.9 pp; memory-level safety filtering achieves a 100% detection rate on our evaluated risky memory entries and restores generation behavior to the without-memory baseline. Based on these findings, we provide actionable suggestions to improve the security of long-term memory in LLM-based code generation.

7 October 2026
Verified
Conference Paper
Open access
YCYuchen Chen
Yuchen Chen
WCWei Cheng
Wei Cheng
YXYuan Xiao
Yuan Xiao
Weisong SunWeisong Sun
Weisong Sun
Chunrong FangChunrong Fang
Chunrong Fang
BXBaowen Xu
Baowen Xu