A Pilot Study on Detecting Software Design Patterns with Large Language Models: An Empirical Evaluation

• URL: http://arxiv.org/abs/2604.17329v1
• Date: Sun, 19 Apr 2026 08:51:29 GMT
• Title: A Pilot Study on Detecting Software Design Patterns with Large Language Models: An Empirical Evaluation
• Abstract summary: This work evaluates the design pattern recognition capabilities of four Large Language Models and two ensemble approaches.<n>We investigate the detection of five design patterns: singleton, adapter, bridge, composite and decorator.<n>Our preliminary results indicate that LLMs show promise for automatically detecting design patterns, with NextCoder and Gemma 3 demonstrating comparatively higher accuracy than other models evaluated.
• Score: 3.4881760143114353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Design patterns provide reusable solutions to recurring software design problems. Automatically detecting these patterns in source code can help bootstrap new developers' understanding of unfamiliar software system architectures, and can help experienced developers to quickly identify and rectify potential quality issues. While many prior research works have explored graph based and machine-learning based detection techniques, this work evaluates the design pattern recognition capabilities of four Large Language Models and two ensemble approaches consisting three out of the four models. We also compare their performance when prompted with a) Source code, b) PlantUML representation of source code, and c) Text-based descriptions of the source code. We investigate the detection of five design patterns: singleton, adapter, bridge, composite and decorator. Our preliminary results indicate that LLMs show promise for automatically detecting design patterns, with NextCoder and Gemma 3 demonstrating comparatively higher accuracy than other models evaluated, and the ensemble approaches enhancing the overall efficiency of design pattern detection. We identify several directions for future work.

Related papers

• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• LOCOFY Large Design Models -- Design to code conversion solution [0.0]
  We introduce the Large Design Models paradigm specifically trained on designs and webpages to enable seamless conversion from design-to-code.<n>We have developed a training and inference pipeline by incorporating data engineering and appropriate model architecture modification.<n>Our models illustrated exceptional end-to-end design-to-code conversion accuracy using a novel preview match score metric.
  arXiv  Detail & Related papers  (2025-07-22T03:54:57Z)
• EnseSmells: Deep ensemble and programming language models for automated code smells detection [3.974095344344234]
  A smell in software source code denotes an indication of suboptimal design and implementation decisions.<n>This paper proposes a novel approach to code smell detection, constructing a deep learning architecture that places importance on the fusion of structural features and statistical semantics.
  arXiv  Detail & Related papers  (2025-02-07T15:35:19Z)
• Automated Microservice Pattern Instance Detection Using Infrastructure-as-Code Artifacts and Large Language Models [0.0]
  This article presents our ongoing PhD research, early experiments, and a prototype for a tool we call MicroPAD for automating the detection of microservice pattern instances.<n>The prototype uses Large Language Models (LLMs) to analyze Infrastructure-as-Code (IaC) artifacts to aid detection, aiming to keep costs low and maximize the scope of detectable patterns.
  arXiv  Detail & Related papers  (2025-02-06T16:22:14Z)
• ViUniT: Visual Unit Tests for More Robust Visual Programming [104.55763189099125]
  When models answer correctly, they produce incorrect programs 33% of the time.<n>We propose Visual Unit Testing (ViUniT), a framework to improve the reliability of visual programs by automatically generating unit tests.
  arXiv  Detail & Related papers  (2024-12-12T01:36:18Z)
• Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering [74.99736967448423]
  We construct Design2Code - the first real-world benchmark for this task.<n>We manually curate 484 diverse real-world webpages as test cases and develop a set of automatic evaluation metrics.<n>Our fine-grained break-down metrics indicate that models mostly lag in recalling visual elements from the input webpages and generating correct layout designs.
  arXiv  Detail & Related papers  (2024-03-05T17:56:27Z)
• CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning [61.21923643289266]
  Chain of Manipulations is a mechanism that enables Vision-Language Models to solve problems step-by-step with evidence.<n>After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) actively without involving external tools.<n>Our trained model, textbfCogCoM, achieves state-of-the-art performance across 9 benchmarks from 4 categories.
  arXiv  Detail & Related papers  (2024-02-06T18:43:48Z)
• Unifying Flow, Stereo and Depth Estimation [121.54066319299261]
  We present a unified formulation and model for three motion and 3D perception tasks. We formulate all three tasks as a unified dense correspondence matching problem. Our model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks.
  arXiv  Detail & Related papers  (2022-11-10T18:59:54Z)
• Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks [28.212889828892664]
  We propose a novel source code model embedded with hierarchical dependencies. We introduce the syntactic structural of the basic block, i.e., its corresponding AST, in source code model to provide sufficient information. The results show that our model reduces the scale of parameters by 50% and achieves 4% improvement on accuracy on program classification task.
  arXiv  Detail & Related papers  (2021-11-20T04:03:42Z)
• A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems [15.654119998970499]
  We propose a template-guided hybrid pointer network for the knowledge-based task-oriented dialogue system. We design a memory pointer network model with a gating mechanism to fully exploit the semantic correlation between the retrieved answers and the ground-truth response.
  arXiv  Detail & Related papers  (2021-06-10T15:49:26Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)

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.