6 papers
An Empirical Study of Interaction Smells in Multi-Turn Human-LLM Collaborative Code Generation
Binquan Zhang, Li Zhang, Lin Shi +6
Large Language Models (LLMs) have revolutionized code generation, evolving from static tools into dynamic conversational interfaces that facilitate complex, multi-turn collaborativ…
Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation
Mohammad Abdollahi, Khandaker Rifah Tasnia, Soumit Kanti Saha +3
Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation,…
Retrieval-Augmented Test Generation: How Far Are We?
Jiho Shin, Nima Shiri Harzevili, Reem Aleithan +2
Retrieval Augmented Generation (RAG) has advanced software engineering tasks but remains underexplored in unit test generation. To bridge this gap, we investigate the efficacy of R…
Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm
Hamed Taherkhani, Melika Sepindband, Hung Viet Pham +2
Large Language Models have seen increasing use in various software development tasks, especially in code generation. The most advanced recent methods attempt to incorporate feedbac…
Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
Melika Sepidband, Hamed Taherkhani, Song Wang +1
Automatic code generation has gained significant momentum with the advent of Large Language Models (LLMs) such as GPT-4. Although many studies focus on improving the effectiveness…
Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
Jiho Shin, Clark Tang, Tahmineh Mohati +3
The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prom…