Chuanyi Li

Towards the Generalizability of Leveraging ChatGPT in APR via Self-enhancing: An Empirical Study

Automated Program Repair (APR) increasingly relies on Large Language Models (LLMs). ChatGPT-enhanced APR uses techniques such as self-correction and autonomous agents to improve repair without modifying model parameters. Although these approaches report strong results on Defects4J and SWE-bench, the stability of enhanc...

Empirical Study of Code Large Language Models for Binary Security Patch Detection

This initial study demonstrates that directly prompting off-the-shelf code LLMs remains ineffective; even advanced prompting strategies cannot compensate for the lack of task-specific knowledge, and fine-tuning proves highly effective, with pseudo-code representation consistently yielding the best performance.

P-NPR: Practical Neural Program Repair via Learning to Ensemble