# Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware

arXiv: https://arxiv.org/abs/2505.05057 · HTML: https://mlsanity.com/paper/2505.05057/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems](https://mlsanity.com/paper/2402.18649/) (2024)
- [PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback](https://mlsanity.com/paper/2307.14936/) (2023)
- [Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?](https://mlsanity.com/paper/2112.12653/) (2021)
- [On Mitigating Code LLM Hallucinations with API Documentation](https://mlsanity.com/paper/2407.09726/) (2024)
- [ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code](https://mlsanity.com/paper/2409.10280/) (2024)
- [Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models](https://mlsanity.com/paper/2106.13928/) (2021)
- [API Usage Recommendation via Multi-View Heterogeneous Graph Representation Learning](https://mlsanity.com/paper/2208.01971/) (2022)

## Built on by (most cited first, 6 of 6)

- [Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries](https://mlsanity.com/paper/2509.22202/) (2025)
- [When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context](https://mlsanity.com/paper/2605.14478/) (2026)
- [Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation](https://mlsanity.com/paper/2605.31478/) (2026)
- [TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development](https://mlsanity.com/paper/2607.18886/) (2026)
- [An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations](https://mlsanity.com/paper/2604.07755/) (2026)
- [LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models](https://mlsanity.com/paper/2606.25402/) (2026)

## Abstract (arXiv)

Application Programming Interfaces (APIs) are crucial in modern software development. Large Language Models (LLMs) assist in automated code generation but often struggle with API hallucination, including invoking non-existent APIs and misusing existing ones in practical development scenarios. Existing studies resort to Retrieval-Augmented Generation (RAG) methods for mitigating the hallucination issue, but tend to fail since they generally ignore the structural dependencies in practical projects and do not indeed validate whether the generated APIs are available or not. To address these limitations, we propose MARIN, a framework for mitigating API hallucination in code generated by LLMs with hierarchical dependency aware. MARIN consists of two phases: Hierarchical Dependency Mining, which analyzes local and global dependencies of the current function, aiming to supplement comprehensive project context in LLMs input, and Dependency Constrained Decoding, which utilizes mined dependencies to adaptively constrain the generation process, aiming to ensure the generated APIs align with the projects specifications. To facilitate the evaluation of the degree of API hallucination, we introduce a new benchmark APIHulBench and two new metrics including Micro Hallucination Number (MiHN) and Macro Hallucination Rate (MaHR). Experiments on six state-of-the-art LLMs demonstrate that MARIN effectively reduces API hallucinations, achieving an average decrease of 67.52% in MiHN and 73.56% in MaHR compared to the RAG approach. Applied to Huaweis internal projects and two proprietary LLMs, MARIN achieves average decreases of 57.33% in MiHN and 59.41% in MaHR.