4 papers · 1 filter
Evaluating LLMs on Java Code Snippet Adaptation Using a Mutation-Injection Framework
Ali Aman, Muhammad Asaduzzaman, Shaowei Wang +1
Background: Developers frequently reuse code by copying fragments and adapting them to fit new contexts. Existing benchmarks for evaluating large language models (LLMs) on code ada…
RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
Mehedi Hasan Shanto, Muhammad Asaduzzaman, Alioune Ngom
User comments on online programming platforms such as Stack Overflow play a vital role in maintaining the correctness and relevance of shared code examples. However, the majority o…
When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation
Ahmed Nusayer Ashik, Shaowei Wang, Tse-Hsun Chen +2
The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. Whi…
Typify: A Lightweight Usage-driven Static Analyzer for Precise Python Type Inference
Ali Aman, Muhammad Asaduzzaman, Shaowei Wang
Python's dynamic type system, while offering significant flexibility and expressiveness, poses substantial challenges for static analysis and automated tooling, particularly in una…