Year: 2024
Type: preprint
Abstract: Although the context length limitation of large language models (LLMs) has been mitigated, it still hinders their application to software development tasks. This study proposes a method incorporating execution traces into RAG for inquiries about source code. Small-scale experiments confirm a tendency for the method to contribute to improving LLM response quality.
Source: arXiv (Cornell University)
Author: Kamiya, Toshihiro
Institutions: Shimane University, University of Shimane
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4394709051