arXiv AI September 15, 2026 By Yitong Zhang, Chengze Li, Ruize Chen, Guowei Yang, Xiaoran Jia, Yijie Ren, Jia Li

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

The paper introduces PriCoder, a method for teaching large language models (LLMs) to effectively use private library APIs for code generation. PriCoder synthesizes training data by constructing a graph and applying two operators—Progressive Graph Evolution to increase diversity and Multidimensional Graph Pruning to enhance quality. Experiments on three mainstream LLMs demonstrate that PriCoder boosts private‑library code generation by over 20% in pass@1, while leaving general code generation largely unchanged.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 4

MAPLE: Metadata Augmented Private Language Evolution

arXiv:2603. 19258v2 Announce Type: replace-cross Abstract: Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users.

By Eli Chien, Yuzheng Hu, Ryan McKenna, Shanshan Wu, Zheng Xu, Peter Kairouz

llms fine-tuning benchmarks safety

arXiv AI

Jul 8

Learning from Execution: Self-Evolving Memory for Private-Library Code Generation

arXiv:2604. 24222v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development relies on internal private libraries absent from public pre-training corpora.

By Mofei Li, Taozhi Chen, Guowei Yang, Jia Li

llms rag safety

arXiv AI

Sep 1

StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Models

arXiv:2508.02601v2 Announce Type: replace-cross Abstract: Tabular data derives its value from inter-feature dependencies, yet preserving them during synthesis is fragile when samples are scarce. Exis...

By Siyi Liu, Yujia Zheng, Haoyang Li, Yongqi Zhang

llms benchmarks safety

arXiv AI

Aug 14

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

arXiv:2603. 14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones.

By Junhang Cheng, Fang Liu, Jia Li, Chengru Wu, Nanxiang Jiang, Li Zhang

llms rag agents benchmarks

arXiv Machine Learning

Aug 6

PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration

arXiv:2608. 04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate.

By Yuyang Xia, Ruixuan Liu, Li Xiong

llms benchmarks safety

arXiv AI

Jun 10

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.

By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

MAPLE: Metadata Augmented Private Language Evolution

Learning from Execution: Self-Evolving Memory for Private-Library Code Generation

StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Models

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration

Advancing the State-of-the-Art in Empirical Privacy Auditing