# Enhancing Project-Specific Code Completion by Inferring Internal API Information

arXiv: https://arxiv.org/abs/2507.20888 · HTML: https://mlsanity.com/paper/2507.20888/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 30 of 31)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow](https://mlsanity.com/paper/1805.08949/) (2018)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation](https://mlsanity.com/paper/2206.02369/) (2022)
- [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://mlsanity.com/paper/2212.10007/) (2022)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [RLCoder: Reinforcement Learning for Repository-Level Code Completion](https://mlsanity.com/paper/2407.19487/) (2024)
- [RepoFusion: Training Code Models to Understand Your Repository](https://mlsanity.com/paper/2306.10998/) (2023)
- [HITS: High-coverage LLM-based Unit Test Generation via Method Slicing](https://mlsanity.com/paper/2408.11324/) (2024)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation](https://mlsanity.com/paper/2401.06391/) (2024)
- [Guiding Language Models of Code with Global Context using Monitors](https://mlsanity.com/paper/2306.10763/) (2023)
- [Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy](https://mlsanity.com/paper/2109.08780/) (2021)
- [DevEval: Evaluating Code Generation in Practical Software Projects](https://mlsanity.com/paper/2401.06401/) (2024)
- [Practitioners' Expectations on Code Completion](https://mlsanity.com/paper/2301.03846/) (2023)

## Built on by (most cited first, 5 of 5)

- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark](https://mlsanity.com/paper/2601.03708/) (2026)
- [GAPO: Robust Advantage Estimation for Real-World Code LLMs](https://mlsanity.com/paper/2510.21830/) (2025)
- [LegacyTranslate: LLM-based Multi-Agent Method for Legacy Code Translation](https://mlsanity.com/paper/2603.14054/) (2026)
- [Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction](https://mlsanity.com/paper/2604.09995/) (2026)

## Abstract (arXiv)

Project-specific code completion is a critical task that leverages context from a project to generate accurate code. State-of-the-art methods use retrieval-augmented generation (RAG) with large language models (LLMs) and project information for code completion. However, they often struggle to incorporate internal API information, which is crucial for accuracy, especially when APIs are not explicitly imported in the file. To address this, we propose a method to infer internal API information without relying on imports. Our method extends the representation of APIs by constructing usage examples and semantic descriptions, building a knowledge base for LLMs to generate relevant completions. We also introduce ProjBench, a benchmark that avoids leaked imports and consists of large-scale real-world projects. Experiments on ProjBench and CrossCodeEval show that our approach significantly outperforms existing methods, improving code exact match by 22.72% and identifier exact match by 18.31%. Additionally, integrating our method with existing baselines boosts code match by 47.80% and identifier match by 35.55%.