12 papers
Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair
S M Farah Al Fahim, Md Nakhla Rafi, Md Ahasanuzzaman +5
Bug reports serve as task specifications for repository-level automated program repair (APR) agents, but they often describe only the observed failure and omit repair-relevant info…
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…
Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding
Pengfei He, Shaowei Wang, Tse-Hsun Chen +1
Static program slicing is a fundamental software engineering technique for isolating code relevant to specific variables. While recent learning-based approaches using language mode…
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…
CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs
Pengfei He, Shaowei Wang, Tse-Hsun Chen
Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tok…
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…