8 papers
Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun +2
LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) pr…
MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
Tiezhu Sun, Marco Alecci, Aleksandr Pilgun +5
The rapid evolution of Android malware poses significant challenges to the maintenance and security of mobile applications (apps). Traditional detection techniques often struggle t…
Measuring LLM Code Generation Stability via Structural Entropy
Yewei Song, Tiezhu Sun, Xunzhu Tang +3
Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entro…
MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
Gong Chen, Wenjie Liu, Xiaoyuan Xie +3
Recently, several studies have indicated that data poisoning attacks pose a severe security threat to deep learning-based (DL-based) code search models. Attackers inject carefully…
Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning
Xunzhu Tang, Jacques Klein, Tegawendé F. Bissyandé
Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks, primarily due to their superior reasoning capabilities and extensive pre…
CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing
Yewei Song, Xunzhu Tang, Cedric Lothritz +6
API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is…