3 papers
cs.SE2026
TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
Yifeng Di, Xuliang Huang, Tianyi Zhang
Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes…
cs.SE2026
Automating API Documentation from Crowdsourced Knowledge
Bonan Kou, Zijie Zhou, Muhao Chen +1
API documentation is crucial for developers to learn and use APIs. However, it is known that many official API documents are obsolete and incomplete. To address this challenge, we…
cs.SE2024
Decide: Knowledge-Based Version Incompatibility Detection in Deep Learning Stacks
Zihan Zhou, Zhongkai Zhao, Bonan Kou +1
Version incompatibility issues are prevalent when reusing or reproducing deep learning (DL) models and applications. Compared with official API documentation, which is often incomp…