mlsanityData to 7 Oct 2026

Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation

arXiv 2506.03535 ↗First posted 4 Jun 2025cs.SEcited by 3

On the map: Retrieval-augmented generation → RAG for code

Abstract (arXiv)

Current research on large language models (LLMs) with retrieval-augmented code generation (RACG) has largely focused on single-language settings, leaving their cross-lingual effectiveness underexplored. Multilingual RACG systems are increasingly important for migrating and reusing code across programming languages (PLs), a common yet challenging task in modern software development. To systematically study cross-lingual code knowledge transfer in RACG, we construct a dataset covering 13 PLs with nearly 14K instances. Our experiments reveal three key insights: (1) Knowledge transfer in RACG across PLs is non-trivial even using direct injection. (2) RACG exhibits unequal cross-lingual knowledge transfer, and its efficacy depends on linguistic affinity of PL pair and diversity of LLM pretraining corpus. (3) RACG shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever. These findings provide practical guidance for designing effective multilingual RACG systems. https://github.com/icip-cas/Cross-Lingual-RACG

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in RAG for code, one of 15 directions in Retrieval-augmented generation. Builds on 47 of its 66 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

47 of 66 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?19 Mar
  2. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities23 Jan
  3. 2024Building A Coding Assistant via the Retrieval-Augmented Language Model21 Oct
  4. 2024Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation24 Sep
  5. 2024Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation7 Aug
  6. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?20 Jun
  7. 2024Prompt-based Code Completion via Multi-Retrieval Augmented Generation13 May
  8. 2024EVOR: Evolving Retrieval for Code Generation19 Feb
  9. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair12 Sep
  10. 2022ReACC: A Retrieval-Augmented Code Completion Framework15 Mar
  11. 2021Retrieval Augmented Code Generation and Summarization26 Aug

Other references · 36

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  8. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  9. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  10. 2023Textbooks Are All You Needcited by 561
  11. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  12. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 527
24 more
  1. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  2. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  3. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  4. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  5. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  6. 2022Multi-lingual Evaluation of Code Generation Modelscited by 158
  7. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
  8. 2021Jigsaw: Large Language Models meet Program Synthesiscited by 103
  9. 2024BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Modelscited by 84
  10. 2023Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Reviewcited by 50
  11. 2023Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMscited by 45
  12. 2023Large Language Model-Aware In-Context Learning for Code Generationcited by 42
  13. 2024McEval: Massively Multilingual Code Evaluationcited by 42
  14. 2024From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injectioncited by 36
  15. 2025Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systemscited by 32
  16. 2024CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Executioncited by 31
  17. 2021Adversarial Robustness of Deep Code Comment Generationcited by 22
  18. 2019A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniquescited by 15
  19. 2024Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative taskscited by 11
  20. 2025Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibilitycited by 10
  21. 2025Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generationcited by 9
  22. 2023Revisiting and Improving Retrieval-Augmented Deep Assertion Generationcited by 5
  23. 2020Challenges in migrating legacy software systems to the cloud an empirical studycited by 3
  24. 2024CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkitcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  2. 2026Beyond Retrieval: A Multitask Benchmark and Model for Code Searchcited by 1
  3. 2026Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encodercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
  2. 2026Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
  3. 2024Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation
  4. 2024Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
  5. 2026Context-Augmented Code Generation Using Programming Knowledge Graphs
  6. 2024Context-Augmented Code Generation Using Programming Knowledge Graphs
  7. 2024Assessing Code Generation with Intermediate Languages
  8. 2024Assessing the Answerability of Queries in Retrieval-Augmented Code Generation