[2Win5] Poster session 2

[2Win5-04] Verification of RAG using Hypothetical Document Embedding in Code Generation Task

〇REO CHIYOMARU¹, Hayato Ogawa¹, Osamu Yoshie¹ (1.Waseda University)

Keywords:Natural Language Processing, Code Generation, RAG

Large Language Models (LLMs) are being utilized for various tasks in software development, including code generation and code completion. While pre-trained and fine-tuned coding-specialized LLMs like Code Llama achieve advanced code generation capabilities, they have limitations in adapting to specific development methodologies and updates in modern programming languages. In this research, to address this challenge, we conducted experiments and evaluations of a RAG system using hypothetical document embeddings. Through this verification, we compared the proposed method with conventional RAG systems and demonstrated the utility and limitations of this new approach in complementing the constraints of coding-specialized models. This approach presents a promising methodology that can contribute to the development of more flexible and accurate code generation systems.