From the 1 of 5 linked papers with an AI index.
5 papers
Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
Large language models (LLMs) can generate functionally useful code that remains vulnerable, while security-focused interventions may break intended behavior. We investigate securit…
Do Code Language Models Use Tests? A Behavioral and Representational Study of Test-Driven Code Generation
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
The paper investigates how code language models respond to test cases in prompts, analyzing whether tests act as executable specifications or merely extra context, and finds that t…
Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR
Yunhao Liang, Ruixuan Ying, Bo Li +7
DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. Whil…
HyClone: Bridging LLM Understanding and Dynamic Execution for Semantic Code Clone Detection
Yunhao Liang, Ruixuan Ying, Takuya Taniguchi +2
Code clone detection is a critical task in software engineering, aimed at identifying duplicated or similar code fragments within or across software systems. Traditional methods of…
Failures Are the Stepping Stones to Success: Enhancing Few-Shot In-Context Learning by Leveraging Negative Samples
Yunhao Liang, Ruixuan Ying, Takuya Taniguchi +1
Large Language Models exhibit powerful few-shot in-context learning (ICL) capabilities, but the performance is highly sensitive to provided examples. Recent research has focused on…