Retrieval-Augmented Generation (RAG)은 외부 지식 소스에서 관련 정보를 검색하여 Large Language Model (LLM) 프롬프트에 추가 컨텍스트로 제공함으로써 환각을 줄이는 기법이다. 그러나 코드는 엄격한 문법 구조와 실행 가능성 조건을 가지므로, 자연어 질의응답(QA)과 달리 관련성이 낮은 예제는 오히려 노이즈로 작용할 수 있어 적절한 RAG 전략이 중요하다. 본 논문에서는 코드 지식의 인덱싱 및 저장, 데이터 관리, 검색, 검색 후 재순위 및 필터링 등의 정제 단계, 코드 생성에 이르는 통합적인 RAG 파이프라인 프레임워크를 설계한다. LiveCodeBench 벤치마크에서 기본 프롬프팅 전략 Direct Prompt과 제안하는 RAG 파이프라인 프레임워크를 활용한 Top-1 Prompt, Threshold-based Prompt를 비교한 결과, Threshold-based Prompt 전략이 대부분의 모델에서 가장 우수하였으나 코딩 특화 모델에서는 RAG 효과가 제한적으로 나타났으며, 모델 자체의 추론 능력에 따라 RAG의 효과가 다르게 작용함을 확인하였다.
KSP Keywords
Language Models
Copyright Policy
ETRI KSP Copyright Policy
The materials provided on this website are subject to copyrights owned by ETRI and protected by the Copyright Act. Any reproduction, modification, or distribution, in whole or in part, requires the prior explicit approval of ETRI. However, under Article 24.2 of the Copyright Act, the materials may be freely used provided the user complies with the following terms:
The materials to be used must have attached a Korea Open Government License (KOGL) Type 4 symbol, which is similar to CC-BY-NC-ND (Creative Commons Attribution Non-Commercial No Derivatives License). Users are free to use the materials only for non-commercial purposes, provided that original works are properly cited and that no alterations, modifications, or changes to such works is made. This website may contain materials for which ETRI does not hold full copyright or for which ETRI shares copyright in conjunction with other third parties. Without explicit permission, any use of such materials without KOGL indication is strictly prohibited and will constitute an infringement of the copyright of ETRI or of the relevant copyright holders.
J. Kim et. al, "Trends in Lightweight Kernel for Many core Based High-Performance Computing", Electronics and Telecommunications Trends. Vol. 32, No. 4, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
J. Sim et.al, “the Fourth Industrial Revolution and ICT – IDX Strategy for leading the Fourth Industrial Revolution”, ETRI Insight, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
If you have any questions or concerns about these terms of use, or if you would like to request permission to use any material on this website, please feel free to contact us
KOGL Type 4:(Source Indication + Commercial Use Prohibition+Change Prohibition)
Contact ETRI, Research Information Service Section
Privacy Policy
ETRI KSP Privacy Policy
ETRI does not collect personal information from external users who access our Knowledge Sharing Platform (KSP). Unathorized automated collection of researcher information from our platform without ETRI's consent is strictly prohibited.
[Researcher Information Disclosure] ETRI publicly shares specific researcher information related to research outcomes, including the researcher's name, department, work email, and work phone number.
※ ETRI does not share employee photographs with external users without the explicit consent of the researcher. If a researcher provides consent, their photograph may be displayed on the KSP.