paper-with-me

Papers

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion

2025-09-19 · Sheng Zhang, Yifan Ding, Shuquan Lian, Shun Song, Hui Li arxiv

Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code completion methods, yielding promising results. Nevertheless, they suffer from issues such as inappropriate query construction, single-path code retrieval, and misalignment between code retriever and code LLM. To address these problems, we introduce CodeRAG, a framework tailored to identify relevant and necessary knowledge for retrieval-augmented repository-level code completion. Its core components include log probability guided query construction, multi-path code retrieval, and preference-aligned BestFit reranking. Extensive experiments on benchmarks ReccEval and CCEval demonstrate that CodeRAG significantly and consistently outperforms state-of-the-art methods. The implementation of CodeRAG is available at https://github.com/KDEGroup/CodeRAG.

📄 PDF Abstract BibTeX arXiv:2509.16112

Code (0)

등록된 구현이 없습니다.

Tasks

Code Completion

Similar Papers 제목 키워드 기반

CodeRAG-Bench: Can Retrieval Augment Code Generation?

2024-06-20 · Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu 외

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documenta…

Code GenerationRAGRetrievalRetrieval-augmented Generation

Assessing "Implicit" Retrieval Robustness of Large Language Models

2024-06-26 · Xiaoyu Shen, Rexhina Blloshmi, Dawei Zhu, Jiahuan Pei 외

Retrieval-augmented generation has gained popularity as a framework to enhance large language models with external knowledge. However, its effectiveness hinges on the retrieval robustness of the model. If the model lacks…

RetrievalRetrieval-augmented Generation

Crafting the Path: Robust Query Rewriting for Information Retrieval

2024-07-17 · Ingeol Baek, JiMin Lee, Joonho Yang, Hwanhee Lee

Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on …

Information RetrievalRetrievalRetrieval-augmented Generation

Thrust: Adaptively Propels Large Language Models with External Knowledge

2023-07-19 · NeurIPS 2023 11

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However…

Information RetrievalRetrieval

Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation

2024-07-16 · Garima Agrawal, Tharindu Kumarage, Zeyad Alghamdi, Huan Liu

Large Language Models (LLMs) are proficient at generating coherent and contextually relevant text but face challenges when addressing knowledge-intensive queries in domain-specific and factual question-answering tasks. R…

Knowledge GraphsQuestion AnsweringRAGRetrieval+1