To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

• URL: http://arxiv.org/abs/2603.15159v3
• Date: Thu, 19 Mar 2026 05:08:18 GMT
• Title: To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
• Abstract summary: Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation.<n>We propose PriCoder, an approach that teaches LLMs to invoke private-library APIs through automatically synthesized data.<n>PriCoder substantially improves private-library-oriented code generation, yielding gains of over 20% in pass@1 in many settings.
• Score: 10.540200819270359
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Our code and benchmarks are publicly available at https://github.com/eniacode/PriCoder.

Related papers

• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Seed-Coder: Let the Code Model Curate Data for Itself [41.69830870792126]
  We introduce Seed-Coder, a series of open-source models of 8B size.<n>Our code pretraining data is produced by a model-centric data pipeline.<n>Seed-Coder achieves state-of-the-art results among open-source models of similar size.
  arXiv  Detail & Related papers  (2025-06-04T03:17:19Z)
• OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models [76.59316249991657]
  Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems.<n>While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs remain limited.<n>We introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
  arXiv  Detail & Related papers  (2024-11-07T17:47:25Z)
• A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models [14.665460257371164]
  Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation. We propose AutoAPIEval, a framework designed to evaluate the capabilities of LLMs in API-oriented code generation.
  arXiv  Detail & Related papers  (2024-09-23T17:22:09Z)
• VersiCode: Towards Version-controllable Code Generation [58.82709231906735]
  Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development. We propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM) We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge.
  arXiv  Detail & Related papers  (2024-06-11T16:15:06Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• Differentially Private Synthetic Data via Foundation Model APIs 2: Text [56.13240830670327]
  A lot of high-quality text data generated in the real world is private and cannot be shared or used freely due to privacy concerns. We propose an augmented PE algorithm, named Aug-PE, that applies to the complex setting of text. Our results demonstrate that Aug-PE produces DP synthetic text that yields competitive utility with the SOTA DP finetuning baselines.
  arXiv  Detail & Related papers  (2024-03-04T05:57:50Z)
• Private-Library-Oriented Code Generation with Large Language Models [52.73999698194344]
  This paper focuses on utilizing large language models (LLMs) for code generation in private libraries. We propose a novel framework that emulates the process of programmers writing private code. We create four private library benchmarks, including TorchDataEval, TorchDataComplexEval, MonkeyEval, and BeatNumEval.
  arXiv  Detail & Related papers  (2023-07-28T07:43:13Z)
• When Language Model Meets Private Library [25.610036042971043]
  In practice, it is common for programmers to write code using private libraries. This is a challenge for language models since they have never seen private APIs during training. We propose a novel framework with two modules: the APIRetriever finds useful APIs, and then the APICoder generates code using these APIs.
  arXiv  Detail & Related papers  (2022-10-31T11:42:06Z)
• CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation [46.45445767488915]
  We show how to leverage an unlabelled code corpus to train a model for library-oriented code generation. We craft two benchmarks named PandasEval and NumpyEval to evaluate library-oriented code generation.
  arXiv  Detail & Related papers  (2022-06-14T14:44:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.