Showing cs.SEShow all
3 papers · 1 filter
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.SE2025
Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
Yifeng Di, Tianyi Zhang
Large Language Models (LLMs) have demonstrated unprecedented capability in code generation. However, LLM-generated code is still plagued with a wide range of functional errors, esp…
cs.SE2023
Software Entity Recognition with Noise-Robust Learning
Tai Nguyen, Yifeng Di, Joohan Lee +2
Recognizing software entities such as library names from free-form text is essential to enable many software engineering (SE) technologies, such as traceability link recovery, auto…