Testing the Untestable? An Empirical Study on the Testing Process of LLM-Powered Software Systems

• URL: http://arxiv.org/abs/2508.00198v2
• Date: Mon, 04 Aug 2025 01:59:04 GMT
• Title: Testing the Untestable? An Empirical Study on the Testing Process of LLM-Powered Software Systems
• Authors: Cleyton Magalhaes, Italo Santos, Brody Stuart-Verner, Ronnie de Souza Santos,
• Abstract summary: This study explores how large language models are tested in the context of real-world application development.<n>Case study was conducted using 99 individual reports written by students who built and deployed LLM-powered applications as part of a university course.<n>Results: Testing LLM-powered systems required adaptations to traditional verification methods, blending source-level reasoning with behavior-aware evaluations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Software systems powered by large language models are becoming a routine part of everyday technologies, supporting applications across a wide range of domains. In software engineering, many studies have focused on how LLMs support tasks such as code generation, debugging, and documentation. However, there has been limited focus on how full systems that integrate LLMs are tested during development. Aims: This study explores how LLM-powered systems are tested in the context of real-world application development. Method: We conducted an exploratory case study using 99 individual reports written by students who built and deployed LLM-powered applications as part of a university course. Each report was independently analyzed using thematic analysis, supported by a structured coding process. Results: Testing strategies combined manual and automated methods to evaluate both system logic and model behavior. Common practices included exploratory testing, unit testing, and prompt iteration. Reported challenges included integration failures, unpredictable outputs, prompt sensitivity, hallucinations, and uncertainty about correctness. Conclusions: Testing LLM-powered systems required adaptations to traditional verification methods, blending source-level reasoning with behavior-aware evaluations. These findings provide evidence on the practical context of testing generative components in software systems.

Related papers

• Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey [69.45421620616486]
  This work presents the first structured taxonomy and analysis of discrete tokenization methods designed for large language models (LLMs)<n>We categorize 8 representative VQ variants that span classical and modern paradigms and analyze their algorithmic principles, training dynamics, and integration challenges with LLM pipelines.<n>We identify key challenges including codebook collapse, unstable gradient estimation, and modality-specific encoding constraints.
  arXiv  Detail & Related papers  (2025-07-21T10:52:14Z)
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics [101.78963920333342]
  We introduce OpenUnlearning, a standardized framework for benchmarking large language models (LLMs) unlearning methods and metrics.<n>OpenUnlearning integrates 9 unlearning algorithms and 16 diverse evaluations across 3 leading benchmarks.<n>We also benchmark diverse unlearning methods and provide a comparative analysis against an extensive evaluation suite.
  arXiv  Detail & Related papers  (2025-06-14T20:16:37Z)
• Evaluating Large Language Models for Real-World Engineering Tasks [75.97299249823972]
  This paper introduces a curated database comprising over 100 questions derived from authentic, production-oriented engineering scenarios.<n>Using this dataset, we evaluate four state-of-the-art Large Language Models (LLMs)<n>Our results show that LLMs demonstrate strengths in basic temporal and structural reasoning but struggle significantly with abstract reasoning, formal modeling, and context-sensitive engineering logic.
  arXiv  Detail & Related papers  (2025-05-12T14:05:23Z)
• Studying and Benchmarking Large Language Models For Log Level Suggestion [49.176736212364496]
  Large Language Models (LLMs) have become a focal point of research across various domains. This paper investigates the impact of characteristics and learning paradigms on the performance of 12 open-source LLMs in log level suggestion.
  arXiv  Detail & Related papers  (2024-10-11T03:52:17Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification is a key element of machine learning applications.<n>We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines.<n>We conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• A Software Engineering Perspective on Testing Large Language Models: Research, Practice, Tools and Benchmarks [2.8061460833143346]
  Large Language Models (LLMs) are rapidly becoming ubiquitous both as stand-alone tools and as components of current and future software systems. To enable usage of LLMs in the high-stake or safety-critical systems of 2030, they need to undergo rigorous testing.
  arXiv  Detail & Related papers  (2024-06-12T13:45:45Z)
• Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study [72.24266814625685]
  We explore the performance of large language models (LLMs) across the entire software development lifecycle with DevEval.<n>DevEval features four programming languages, multiple domains, high-quality data collection, and carefully designed and verified metrics for each task.<n> Empirical studies show that current LLMs, including GPT-4, fail to solve the challenges presented within DevEval.
  arXiv  Detail & Related papers  (2024-03-13T15:13:44Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• RITFIS: Robust input testing framework for LLMs-based intelligent software [6.439196068684973]
  RITFIS is the first framework designed to assess the robustness of intelligent software against natural language inputs. RITFIS adapts 17 automated testing methods, originally designed for Deep Neural Network (DNN)-based intelligent software. It demonstrates the effectiveness of RITFIS in evaluating LLM-based intelligent software through empirical validation.
  arXiv  Detail & Related papers  (2024-02-21T04:00:54Z)
• A Case Study on Test Case Construction with Large Language Models: Unveiling Practical Insights and Challenges [2.7029792239733914]
  This paper examines the application of Large Language Models in the construction of test cases within the context of software engineering. Through a blend of qualitative and quantitative analyses, this study assesses the impact of LLMs on test case comprehensiveness, accuracy, and efficiency.
  arXiv  Detail & Related papers  (2023-12-19T20:59:02Z)
• Are We Testing or Being Tested? Exploring the Practical Applications of Large Language Models in Software Testing [0.0]
  A Large Language Model (LLM) represents a cutting-edge artificial intelligence model that generates coherent content. LLM can play a pivotal role in software development, including software testing. This study explores the practical application of LLMs in software testing within an industrial setting.
  arXiv  Detail & Related papers  (2023-12-08T06:30:37Z)
• The Integration of Machine Learning into Automated Test Generation: A Systematic Mapping Study [15.016047591601094]
  We characterize emerging research, examining testing practices, researcher goals, ML techniques applied, evaluation, and challenges. ML generates input for system, GUI, unit, performance, and testing or improves the performance of existing generation methods.
  arXiv  Detail & Related papers  (2022-06-21T09:26:25Z)

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.