看见并不等于掌握：教导大语言模型使用私有库进行代码生成

Computer Science > Software Engineering arXiv:2603.15159 (cs) [Submitted on 16 Mar 2026 (v1), last revised 13 Sep 2026 (this version, v5)] Title:To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation Authors:Yitong Zhang, Chengze Li, Ruize Chen, Guowei Yang, Xiaoran Jia, Yijie Ren, Jia Li View a PDF of the paper titled To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation, by Yitong Zhang and 6 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation, where the goal is to generate code using APIs from private libraries. Existing approaches mainly rely on retrieving private-library API documentation and injecting relevant knowledge into the context at inference time. However, our study shows that this is insufficient: even given accurate required knowledge, LLMs still struggle to invoke private-library APIs effectively. To address this limitation, we propose PriCoder, an approach that teaches LLMs to invoke private-library APIs through automatically synthesized data. Specifically, PriCoder models private-library data synthesis as the construction of a graph, and alternates between two graph operators: (1) Progressive Graph Evolution, which improves data diversity by progressively synthesizing more diverse training samples from basic ones, and (2) Multidimensional Graph Pruning, which improves data quality through a rigorous filtering pipeline. To support rigorous evaluation, we construct two new benchmarks based on recently released libraries that are unfamiliar to the tested models. Experiments on three mainstream LLMs show that PriCoder substantially improves private-library-oriented code generation, yielding gains of over 20% in pass@1 in many settings, while causing negligible impact on general code generation capability. Comments: Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2603.15159 [cs.SE] (or arXiv:2603.15159v5 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2603.15159 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yitong Zhang [view email] [v1] Mon, 16 Mar 2026 11:53:39 UTC (948 KB) [v2] Tue, 17 Mar 2026 06:49:54 UTC (948 KB) [v3] Thu, 19 Mar 2026 05:08:18 UTC (959 KB) [v4] Fri, 27 Mar 2026 09:32:08 UTC (953 KB) [v5] Sun, 13 Sep 2026 04:25:59 UTC (1,233 KB) Full-text links: Access Paper: View a PDF of the paper titled To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation, by Yitong Zhang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.SE new | recent | 2026-03 Change to browse by: cs cs.AI cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)