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

arXiv:2603.15159 · cs.SE, cs.AI, cs.CL · Submitted 2026-03-16 · Read on arXiv

cs.SE, cs.AI, cs.CL

Submitted: 2026-03-16

Updated: 2026-09-13

Comments: Submitted to ACM TOSEM

Code: https://github.com/eniacode/PriCoder

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 42× in this paper · explained in 2 episodes
• Pruning — 33× in this paper · explained in 4 episodes
• RAG — 24× in this paper · explained in 3 episodes
• Verification — 19× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Adam — 6× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 5× in this paper · explained in 3 episodes
• Ablation study — 4× in this paper · explained in 1 episode
• Large Language Models (LLMs) — 4× in this paper · explained in 6 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Distillation — 3× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation — 3× in this paper
• Accuracy — 2× in this paper · explained in 1 episode
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Task Decomposition — 2× in this paper · explained in 2 episodes
• Abstract Syntax Tree — 1× in this paper
• Benchmarking — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes

Sources

• Multi-lingual Evaluation of Code Generation Models
• AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation
• CodeT: Code Generation with Generated Tests
• Evaluating Large Language Models Trained on Code
• Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges
• Are We on the Right Way to Assessing LLM-as-a-Judge?
• The Llama 3 Herd of Models
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Qwen2.5-Coder Technical Report
• GPT-4o System Card
• KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?
• Exploring the Potential of Diffusion Large Language Models in Code Generation
• What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
• DeepSeek-V3 Technical Report
• Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
• Decoupled Weight Decay Regularization
• WizardCoder: Empowering Code Large Language Models with Evol-Instruct
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• Contextual API Completion for Unseen Repositories Using LLMs
• Code Llama: Open Foundation Models for Code

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties