When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?

• URL: http://arxiv.org/abs/2503.15231v1
• Date: Wed, 19 Mar 2025 14:08:47 GMT
• Title: When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?
• Authors: Jingyi Chen, Songqiang Chen, Jialun Cao, Jiasi Shen, Shing-Chi Cheung,
• Abstract summary: Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge.<n>We study the factors that affect the effectiveness of using the documentation of less common API libraries as additional knowledge for retrieval and generation.
• Score: 10.204379646375182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) has increasingly shown its power in extending large language models' (LLMs') capability beyond their pre-trained knowledge. Existing works have shown that RAG can help with software development tasks such as code generation, code update, and test generation. Yet, the effectiveness of adapting LLMs to fast-evolving or less common API libraries using RAG remains unknown. To bridge this gap, we take an initial step to study this unexplored yet practical setting - when developers code with a less common library, they often refer to its API documentation; likewise, when LLMs are allowed to look up API documentation via RAG, to what extent can LLMs be advanced? To mimic such a setting, we select four less common open-source Python libraries with a total of 1017 eligible APIs. We study the factors that affect the effectiveness of using the documentation of less common API libraries as additional knowledge for retrieval and generation. Our intensive study yields interesting findings: (1) RAG helps improve LLMs' performance by 83%-220%. (2) Example code contributes the most to advance LLMs, instead of the descriptive texts and parameter lists in the API documentation. (3) LLMs could sometimes tolerate mild noises (typos in description or incorrect parameters) by referencing their pre-trained knowledge or document context. Finally, we suggest that developers pay more attention to the quality and diversity of the code examples in the API documentation. The study sheds light on future low-code software development workflows.

Related papers

• LRASGen: LLM-based RESTful API Specification Generation [3.420331911153286]
  We propose a novel approach for generating the OpenAPI Specification (OAS) specifications for APIs using Large Language Models (LLMs) Compared with existing tools and methods, LRASGen can generate the OASs, even when the implementation is incomplete (with partial code, annotations/comments, etc.) LRASGen-generated specifications cover an average of 48.85% more missed entities than the developer-provided specifications.
  arXiv  Detail & Related papers  (2025-04-23T15:52:50Z)
• Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models [49.214291813478695]
  Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like overflows and use buffer-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries. We propose DFUZZ, an LLM-driven fuzzing approach for DL libraries.
  arXiv  Detail & Related papers  (2025-01-08T07:07:22Z)
• ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration [70.26807758443675]
  ExploraCoder is a training-free framework that empowers large language models to invoke unseen APIs in code solution.<n>We show that ExploraCoder significantly improves performance for models lacking prior API knowledge, achieving an absolute increase of 11.24% over niave RAG approaches and 14.07% over pretraining methods in pass@10.
  arXiv  Detail & Related papers  (2024-12-06T19:00:15Z)
• 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)
• Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding [61.45448947483328]
  We introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER) LASER features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens. LASER achieves a 3-5x speedup on public datasets and saves about 67% of computational resources during the online A/B test.
  arXiv  Detail & Related papers  (2024-08-11T02:31:13Z)
• CodeUpdateArena: Benchmarking Knowledge Editing on API Updates [77.81663273436375]
  We present CodeUpdateArena, a benchmark for knowledge editing in the code domain. An instance in our benchmark consists of a synthetic API function update paired with a program synthesis example. Our benchmark covers updates of various types to 54 functions from seven diverse Python packages.
  arXiv  Detail & Related papers  (2024-07-08T17:55:04Z)
• LLMs Meet Library Evolution: Evaluating Deprecated API Usage in LLM-based Code Completion [13.633501449498402]
  Decomposing API usage is a problem in large language models (LLMs)-based code completion.<n>This study involved seven advanced LLMs, 145 API mappings from eight popular Python libraries, and 28,125 completion prompts.<n>We propose two lightweight fixing approaches, REPLACEAPI and INSERTPROMPT, which can serve as baseline approaches for future research.
  arXiv  Detail & Related papers  (2024-06-14T08:44:10Z)
• Compositional API Recommendation for Library-Oriented Code Generation [23.355509276291198]
  We propose CAPIR, which adopts a "divide-and-conquer" strategy to recommend APIs for coarse-grained requirements. We present two challenging benchmarks, RAPID (Recommend APIs based on Documentation) and LOCG (Library-Oriented Code Generation) Experimental results on these benchmarks, demonstrate the effectiveness of CAPIR in comparison to existing baselines.
  arXiv  Detail & Related papers  (2024-02-29T18:27:27Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• LLatrieval: LLM-Verified Retrieval for Verifiable Generation [67.93134176912477]
  Verifiable generation aims to let the large language model (LLM) generate text with supporting documents. We propose LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-14T01:38:02Z)
• 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)

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.