5 papers
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
QiHong Chen, Aaron Imani, Iftekhar Ahmed
Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval me…
From Bias To Improved Prompts: A Case Study of Bias Mitigation of Clone Detection Models
QiHong Chen, Lianghao Jiang, Iftekhar Ahmed
The issue of clone code has persisted in software engineering, primarily because developers often copy and paste code segments. This common practice has elevated the importance of…
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…
Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks
Jina Chun, Yong Jin Chun, Qihong Chen +2
Large Language Models (LLMs) have advanced autonomous agents' planning and decision-making, yet they struggle with complex tasks requiring diverse expertise and multi-step reasonin…
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…