---
title: "RepoCoder — paper by Zhang et al. (2023) — summary and ideas"
description: "The authors also release RepoEval, a benchmark built from recent GitHub Python repositories. 40 references, cited by 109 papers here."
authors: ["Fengji Zhang", "Bei Chen", "Yue Zhang", "Jacky Keung", "Jin Liu", "Daoguang Zan", "Yi Mao", "Jian-Guang Lou", "Weizhu Chen"]
year: 2023
venue: "arXiv:2303.12570"
source: "https://arxiv.org/abs/2303.12570"
doi: "10.48550/arxiv.2303.12570"
arxiv: "2303.12570"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2023-repocoder-repository-level-code-completion/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2023-repocoder-repository-level-code-completion/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/7/) / RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

# RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

**Authors:** Fengji Zhang, [Bei Chen](https://md.research.elamur.ai/free/en/authors/bei-chen/), [Yue Zhang](https://md.research.elamur.ai/free/en/authors/yue-zhang/), Jacky Keung, Jin Liu, [Daoguang Zan](https://md.research.elamur.ai/free/en/authors/daoguang-zan/), [Yi Mao](https://md.research.elamur.ai/free/en/authors/yi-mao/), [Jian-Guang Lou](https://md.research.elamur.ai/free/en/authors/jian-guang-lou/) and [Weizhu Chen](https://md.research.elamur.ai/free/en/authors/weizhu-chen/) · **Year:** 2023 · **Venue:** arXiv:2303.12570 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2303.12570) · [PDF](https://arxiv.org/pdf/2303.12570) · [DOI 10.48550/arxiv.2303.12570](https://doi.org/10.48550/arxiv.2303.12570) · [arXiv 2303.12570](https://arxiv.org/abs/2303.12570) · [OpenAlex](https://openalex.org/W4360834937)

**Citations:** 10 citations (OpenAlex, 2026-10-14) · [109](https://md.research.elamur.ai/free/en/papers/zhang-2023-repocoder-repository-level-code-completion/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most code completion tools see only the current file. Useful hints such as shared helpers, API signatures and project-specific naming are spread across the rest of the repository. RepoCoder uses this wider context without fine-tuning, static analysis or hand-written rules. It cuts repository files into overlapping snippets with a sliding window, retrieves the snippets most similar to the code being written, and adds them to the prompt of a frozen pre-trained code model. The key idea is iteration. The model's first draft, even if incorrect, is added to the next retrieval query, which steers the search toward what actually needs to be written, and then the model generates again. The authors also release RepoEval, a benchmark built from recent GitHub Python repositories. It covers line, API invocation and function body completion, and function bodies are checked with the repositories' own unit tests. With GPT-3.5-Turbo and CodeGen, RepoCoder beats In-File completion by more than 10% in every setting and consistently outperforms single-pass retrieval-augmented generation (RAG). This makes it a cheap, model-agnostic way to give LLM completion awareness of the whole repository.

## Key points
- **RepoEval structure:** 14 permissively or openly licensed GitHub repositories created in 2022, with statistics taken in January 2023.
  - 8 repositories (e.g., rl, vizier, diffusers, nerfstudio, FedScope) supply 400 line and API invocation samples each.
  - 6 repositories (e.g., imagen, tracr, redframes) supply function body tasks, which are scored by running unit tests rather than by similarity metrics.
- **Retrieval mechanism:** a sliding window of S_w lines moves in steps of S_s.
  - The first query is the last S_w lines of unfinished code.
  - Later queries join the last S_w−S_s lines of that code with the first S_s lines of the previous prediction.
  - Retrieved snippets appear in the prompt with their file paths, in ascending order of similarity.
- **Results:** with GPT-3.5-Turbo and CodeGen, RepoCoder improves on the In-File baseline by over 10% across all settings, and two iterations already beat vanilla RAG.
- **Limitations noted by the authors:**
  - Gains are small in repositories with little code duplication.
  - Performance can become unstable after more iterations, and there is no good stopping rule yet.
  - Each extra round adds latency.
  - Only similarity-based retrievers were tested, and newer models such as GPT-4 and StarCoder were not.
- **Availability:** code and benchmark are public at github.com/microsoft/CodeT (RepoCoder folder).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 378 works · 161,630 citations
- [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) — University, Hong Kong, China · 59 works · 3,480 citations
- [Wuhan University](https://md.research.elamur.ai/free/en/universities/wuhan-university/) — University, Wuhan, China · 47 works · 1,246 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works · [💻 Software](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) · 119 works

🧭 Topics (1): [💻 Code & programming languages](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · 168 works

## Cite

Cite as: Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou and Weizhu Chen. 2023. RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation. arXiv:2303.12570.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{zhang2023repocoder,
  title = {{RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation}},
  author = {Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou and Weizhu Chen},
  year = {2023},
  doi = {10.48550/arxiv.2303.12570},
  eprint = {2303.12570},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2303.12570}
}
```

- [← previous LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://md.research.elamur.ai/free/en/papers/phute-2023-llm-self-defense-self-examination/)
- [next → A Length-Extrapolatable Transformer](https://md.research.elamur.ai/free/en/papers/sun-2023-length-extrapolatable-transformer/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/7/)

## References

40 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
2. Bei Chen, Fengji Zhang, Anh Nguyen, Daoguang Zan, Zeqi Lin, Jian-Guang Lou, and Weizhu Chen. 2022. Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397. [find](https://scholar.google.com/scholar?q=Bei+Chen%2C+Fengji+Zhang%2C+Anh+Nguyen%2C+Daoguang+Zan%2C+Zeqi+Lin%2C+Jian%2DGuang+Lou%2C+and+Weizhu+Chen%2E+2022%2E+Codet%3A+Code+generation+with+generated+tests%2E+arXiv+preprint+arXiv%3A2207%2E10397%2E)
3. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374.
4. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). arXiv preprint arXiv:2204.02311.
5. Colin B Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, and Alexey Svyatkovskiy. 2021. Long-range modeling of source code files with ewash: Extended window access by syntax hierarchy. arXiv preprint arXiv:2109.08780. [find](https://scholar.google.com/scholar?q=Colin+B+Clement%2C+Shuai+Lu%2C+Xiaoyu+Liu%2C+Michele+Tufano%2C+Dawn+Drain%2C+Nan+Duan%2C+Neel+Sundaresan%2C+and+Alexey+Svyatkovskiy%2E+2021%2E+Long%2Drange+modeling+of+source+code+files+with+ewash%3A+Extended+window+access)
6. Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang. 2022. [Cocomic: Code completion by jointly modeling in-file and cross-file context](https://md.research.elamur.ai/free/en/papers/ding-2024-cocomic-code-completion-jointly-modeling/). arXiv preprint arXiv:2212.10007.
7. Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, and Jian Yin. 2022. [Unixcoder: Unified cross-modal pre-training for code representation](https://md.research.elamur.ai/free/en/papers/guo-2022-unixcoder-unified-cross-modal-pre/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7212–7225.
8. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. [Retrieval augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). In International conference on machine learning, pages 3929–3938. PMLR.
9. Vincent J Hellendoorn and Premkumar Devanbu. 2017. Are deep neural networks the best choice for modeling source code? In Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering, pages 763–773. [find](https://scholar.google.com/scholar?q=Vincent+J+Hellendoorn+and+Premkumar+Devanbu%2E+2017%2E+Are+deep+neural+networks+the+best+choice+for+modeling+source+code%3F+In+Proceedings+of+the+2017+11th+Joint+Meeting+on+Foundations+of+Software+Engineeri)
10. Vincent J Hellendoorn, Sebastian Proksch, Harald C Gall, and Alberto Bacchelli. 2019. When code completion fails: A case study on real-world completions. In 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE), pages 960–970. IEEE. [find](https://scholar.google.com/scholar?q=Vincent+J+Hellendoorn%2C+Sebastian+Proksch%2C+Harald+C+Gall%2C+and+Alberto+Bacchelli%2E+2019%2E+When+code+completion+fails%3A+A+case+study+on+real%2Dworld+completions%2E+In+2019+IEEE%2FACM+41st+International+Conference)
11. Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. [Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). arXiv preprint arXiv:2208.03299.
12. Paul Jaccard. 1912. The distribution of the flora in the alpine zone. 1. New phytologist, 11(2):37–50. [find](https://scholar.google.com/scholar?q=Paul+Jaccard%2E+1912%2E+The+distribution+of+the+flora+in+the+alpine+zone%2E+1%2E+New+phytologist%2C+11%282%29%3A37%E2%80%9350%2E)
13. Vladimir I Levenshtein et al. 1966. Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady, volume 10, pages 707–710. Soviet Union. [find](https://scholar.google.com/scholar?q=Vladimir+I+Levenshtein+et+al%2E+1966%2E+Binary+codes+capable+of+correcting+deletions%2C+insertions%2C+and+reversals%2E+In+Soviet+physics+doklady%2C+volume+10%2C+pages+707%E2%80%93710%2E+Soviet+Union%2E)
14. Yoav Levine, Itay Dalmedigos, Ori Ram, Yoel Zeldes, Daniel Jannai, Dor Muhlgay, Yoni Osin, Opher Lieber, Barak Lenz, Shai Shalev-Shwartz, et al. 2022. Standing on the shoulders of giant frozen language models. arXiv preprint arXiv:2204.10019. — [arXiv:2204.10019](https://arxiv.org/abs/2204.10019) [find](https://scholar.google.com/scholar?q=Yoav+Levine%2C+Itay+Dalmedigos%2C+Ori+Ram%2C+Yoel+Zeldes%2C+Daniel+Jannai%2C+Dor+Muhlgay%2C+Yoni+Osin%2C+Opher+Lieber%2C+Barak+Lenz%2C+Shai+Shalev%2DShwartz%2C+et+al%2E+2022%2E+Standing+on+the+shoulders+of+giant+frozen+languag)
15. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in Neural Information Processing Systems, 33:9459–9474.
16. Dong Li, Yelong Shen, Ruoming Jin, Yi Mao, Kuan Wang, and Weizhu Chen. 2022. Generation-augmented query expansion for code retrieval. arXiv preprint arXiv:2212.10692. — [arXiv:2212.10692](https://arxiv.org/abs/2212.10692) [find](https://scholar.google.com/scholar?q=Dong+Li%2C+Yelong+Shen%2C+Ruoming+Jin%2C+Yi+Mao%2C+Kuan+Wang%2C+and+Weizhu+Chen%2E+2022%2E+Generation%2Daugmented+query+expansion+for+code+retrieval%2E+arXiv+preprint+arXiv%3A2212%2E10692%2E+%E2%80%94+%5BarXiv%3A2212%2E10692%5D%28https%3A%2F%2Farxi)
17. Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161. [find](https://scholar.google.com/scholar?q=Raymond+Li%2C+Loubna+Ben+Allal%2C+Yangtian+Zi%2C+Niklas+Muennighoff%2C+Denis+Kocetkov%2C+Chenghao+Mou%2C+Marc+Marone%2C+Christopher+Akiki%2C+Jia+Li%2C+Jenny+Chim%2C+et+al%2E+2023%2E+Starcoder%3A+may+the+source+be+with+you%21+arX)
18. Fang Liu, Ge Li, Zhiyi Fu, Shuai Lu, Yiyang Hao, and Zhi Jin. 2022. Learning to recommend method names with global context. In Proceedings of the 44th International Conference on Software Engineering, pages 1294–1306. [find](https://scholar.google.com/scholar?q=Fang+Liu%2C+Ge+Li%2C+Zhiyi+Fu%2C+Shuai+Lu%2C+Yiyang+Hao%2C+and+Zhi+Jin%2E+2022%2E+Learning+to+recommend+method+names+with+global+context%2E+In+Proceedings+of+the+44th+International+Conference+on+Software+Engineering%2C)
19. Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, and Alexey Svyatkovskiy. 2022. [Reacc: A retrieval-augmented code completion framework](https://md.research.elamur.ai/free/en/papers/lu-2022-reacc-retrieval-augmented-code-completion/). arXiv preprint arXiv:2203.07722.
20. Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664. [find](https://scholar.google.com/scholar?q=Shuai+Lu%2C+Daya+Guo%2C+Shuo+Ren%2C+Junjie+Huang%2C+Alexey+Svyatkovskiy%2C+Ambrosio+Blanco%2C+Colin+Clement%2C+Dawn+Drain%2C+Daxin+Jiang%2C+Duyu+Tang%2C+et+al%2E+2021%2E+Codexglue%3A+A+machine+learning+benchmark+dataset+for+co)
21. Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2023. Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568. [find](https://scholar.google.com/scholar?q=Ziyang+Luo%2C+Can+Xu%2C+Pu+Zhao%2C+Qingfeng+Sun%2C+Xiubo+Geng%2C+Wenxiang+Hu%2C+Chongyang+Tao%2C+Jing+Ma%2C+Qingwei+Lin%2C+and+Daxin+Jiang%2E+2023%2E+Wizardcoder%3A+Empowering+code+large+language+models+with+evol%2Dinstruct%2E+a)
22. Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, and Weizhu Chen. 2020. [Generation-augmented retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/mao-2020-generation-augmented-retrieval-open-domain/). arXiv preprint arXiv:2009.08553.
23. Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474. [find](https://scholar.google.com/scholar?q=Erik+Nijkamp%2C+Bo+Pang%2C+Hiroaki+Hayashi%2C+Lifu+Tu%2C+Huan+Wang%2C+Yingbo+Zhou%2C+Silvio+Savarese%2C+and+Caiming+Xiong%2E+2022%2E+Codegen%3A+An+open+large+language+model+for+code+with+multi%2Dturn+program+synthesis%2E+arX)
24. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/).
25. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). arXiv preprint arXiv:2302.00083.
26. Veselin Raychev, Martin Vechev, and Eran Yahav. 2014. Code completion with statistical language models. In Proceedings of the 35th ACM SIGPLAN conference on programming language design and implementation, pages 419–428. [find](https://scholar.google.com/scholar?q=Veselin+Raychev%2C+Martin+Vechev%2C+and+Eran+Yahav%2E+2014%2E+Code+completion+with+statistical+language+models%2E+In+Proceedings+of+the+35th+ACM+SIGPLAN+conference+on+programming+language+design+and+implementat)
27. Md Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. [Retrieval augmented code generation and summarization](https://md.research.elamur.ai/free/en/papers/parvez-2021-retrieval-augmented-code-generation-summarization/). arXiv e-prints, pages arXiv–2108.
28. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). arXiv preprint arXiv:2301.12652.
29. Disha Shrivastava, Hugo Larochelle, and Daniel Tarlow. 2022. Repository-level prompt generation for large language models of code. arXiv preprint arXiv:2206.12839. — [arXiv:2206.12839](https://arxiv.org/abs/2206.12839) [find](https://scholar.google.com/scholar?q=Disha+Shrivastava%2C+Hugo+Larochelle%2C+and+Daniel+Tarlow%2E+2022%2E+Repository%2Dlevel+prompt+generation+for+large+language+models+of+code%2E+arXiv+preprint+arXiv%3A2206%2E12839%2E+%E2%80%94+%5BarXiv%3A2206%2E12839%5D%28https%3A%2F%2Farxiv%2Eo)
30. Alexey Svyatkovskiy, Shao Kun Deng, Shengyu Fu, and Neel Sundaresan. 2020. Intellicode compose: Code generation using transformer. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pages 1433–1443. [find](https://scholar.google.com/scholar?q=Alexey+Svyatkovskiy%2C+Shao+Kun+Deng%2C+Shengyu+Fu%2C+and+Neel+Sundaresan%2E+2020%2E+Intellicode+compose%3A+Code+generation+using+transformer%2E+In+Proceedings+of+the+28th+ACM+Joint+Meeting+on+European+Software+Eng)
31. Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi, Maik Riechert, Juliana Vicente Franco, and Miltiadis Allamanis. 2021. Fast and memory-efficient neural code completion. In 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), pages 329–340. IEEE. [find](https://scholar.google.com/scholar?q=Alexey+Svyatkovskiy%2C+Sebastian+Lee%2C+Anna+Hadjitofi%2C+Maik+Riechert%2C+Juliana+Vicente+Franco%2C+and+Miltiadis+Allamanis%2E+2021%2E+Fast+and+memory%2Defficient+neural+code+completion%2E+In+2021+IEEE%2FACM+18th+Intern)
32. Alexey Svyatkovskiy, Ying Zhao, Shengyu Fu, and Neel Sundaresan. 2019. Pythia: Ai-assisted code completion system. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2727–2735. [find](https://scholar.google.com/scholar?q=Alexey+Svyatkovskiy%2C+Ying+Zhao%2C+Shengyu+Fu%2C+and+Neel+Sundaresan%2E+2019%2E+Pythia%3A+Ai%2Dassisted+code+completion+system%2E+In+Proceedings+of+the+25th+ACM+SIGKDD+international+conference+on+knowledge+discovery)
33. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. [Lamda: Language models for dialog applications](https://md.research.elamur.ai/free/en/papers/thoppilan-2022-lamda-language-models-dialog-applications/). arXiv preprint arXiv:2201.08239.
34. Zhaopeng Tu, Zhendong Su, and Premkumar Devanbu. 2014. On the localness of software. In Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering, pages 269– 280. [find](https://scholar.google.com/scholar?q=Zhaopeng+Tu%2C+Zhendong+Su%2C+and+Premkumar+Devanbu%2E+2014%2E+On+the+localness+of+software%2E+In+Proceedings+of+the+22nd+ACM+SIGSOFT+International+Symposium+on+Foundations+of+Software+Engineering%2C+pages+269%E2%80%93+2)
35. Liang Wang, Nan Yang, and Furu Wei. 2023. [Query2doc: Query expansion with large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-query2doc-query-expansion-large-language/). arXiv preprint arXiv:2303.07678.
36. Daoguang Zan, Bei Chen, Zeqi Lin, Bei Guan, Yongji Wang, and Jian-Guang Lou. 2022. When language model meets private library. arXiv preprint arXiv:2210.17236. [find](https://scholar.google.com/scholar?q=Daoguang+Zan%2C+Bei+Chen%2C+Zeqi+Lin%2C+Bei+Guan%2C+Yongji+Wang%2C+and+Jian%2DGuang+Lou%2E+2022%2E+When+language+model+meets+private+library%2E+arXiv+preprint+arXiv%3A2210%2E17236%2E)
37. Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, and Fei Sha. 2022. Generate-and-retrieve: Use your predictions to improve retrieval for semantic parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages… [find](https://scholar.google.com/scholar?q=Yury+Zemlyanskiy%2C+Michiel+de+Jong%2C+Joshua+Ainslie%2C+Panupong+Pasupat%2C+Peter+Shaw%2C+Linlu+Qiu%2C+Sumit+Sanghai%2C+and+Fei+Sha%2E+2022%2E+Generate%2Dand%2Dretrieve%3A+Use+your+predictions+to+improve+retrieval+for+seman)
38. Yizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang, Chris Brockett, Michel Galley, Jianfeng Gao, and Bill Dolan. 2022. Retgen: A joint framework for retrieval and grounded text generation modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11739–11747. [find](https://scholar.google.com/scholar?q=Yizhe+Zhang%2C+Siqi+Sun%2C+Xiang+Gao%2C+Yuwei+Fang%2C+Chris+Brockett%2C+Michel+Galley%2C+Jianfeng+Gao%2C+and+Bill+Dolan%2E+2022%2E+Retgen%3A+A+joint+framework+for+retrieval+and+grounded+text+generation+modeling%2E+In+Proce)
39. Shuyan Zhou, Uri Alon, Frank F Xu, Zhengbao JIang, and Graham Neubig. 2022. Doccoder: Generating code by retrieving and reading docs. arXiv preprint arXiv:2207.05987. [find](https://scholar.google.com/scholar?q=Shuyan+Zhou%2C+Uri+Alon%2C+Frank+F+Xu%2C+Zhengbao+JIang%2C+and+Graham+Neubig%2E+2022%2E+Doccoder%3A+Generating+code+by+retrieving+and+reading+docs%2E+arXiv+preprint+arXiv%3A2207%2E05987%2E)
40. Weiqin Zou, Jifeng Xuan, Xiaoyuan Xie, Zhenyu Chen, and Baowen Xu. 2019. How does code style inconsistency affect pull request integration? an exploratory study on 117 github projects. Empirical Software Engineering, 24:3871–3903. [find](https://scholar.google.com/scholar?q=Weiqin+Zou%2C+Jifeng+Xuan%2C+Xiaoyuan+Xie%2C+Zhenyu+Chen%2C+and+Baowen+Xu%2E+2019%2E+How+does+code+style+inconsistency+affect+pull+request+integration%3F+an+exploratory+study+on+117+github+projects%2E+Empirical+Softw)

*Updated 2 November 2026*