most citedAn Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?

1 citations · 1 across the 4 of their papers we have counts for

collaborators

6 papers

cs.SE2025

Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks

E. G. Santana, Gabriel Benjamin, Melissa Araujo +7

A growing variety of prompt engineering techniques has been proposed for Large Language Models (LLMs), yet systematic evaluation of each technique on individual software engineerin…

cs.SE2025

Consider What Humans Consider: Optimizing Commit Message Leveraging Contexts Considered By Human

Jiawei Li, David Faragó, Christian Petrov +1

Commit messages are crucial in software development, supporting maintenance tasks and communication among developers. While Large Language Models (LLMs) have advanced Commit Messag…

cs.SE2025

Optimization is Better than Generation: Optimizing Commit Message Leveraging Human-written Commit Message

Jiawei Li, David Faragó, Christian Petrov +1

Commit messages are crucial in software development, supporting maintenance tasks and communication among developers. While Large Language Models (LLMs) have advanced Commit Messag…

cs.SE20241 cited

An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?

Hyunjae Suh, Mahan Tafreshipour, Jiawei Li +2

Artificial Intelligence (AI) techniques, especially Large Language Models (LLMs), have started gaining popularity among researchers and software developers for generating source co…

cs.SE2024

A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?

QiHong Chen, Jiachen Yu, Jiawei Li +3

Recent advancements in Large Language Models (LLMs) have led to their widespread application in automated code generation. However, these models can still generate defective code t…

cs.SE2024

Does the Order of Fine-tuning Matter and Why?

Qihong Chen, Jiawei Li, Hyunjae Suh +5

To improve the performance on a target task, researchers have fine-tuned language models with an intermediate task before the target task of interest. However, previous works have…