Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy

• URL: http://arxiv.org/abs/2503.00481v1
• Date: Sat, 01 Mar 2025 13:15:56 GMT
• Title: Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy
• Authors: Felix Dobslaw, Robert Feldt, Juyeon Yoon, Shin Yoo,
• Abstract summary: Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software.<n>This paper presents a taxonomy for LLM test case design, informed by both the research literature, our experience, and open-source tools that represent the state of practice.
• Score: 14.041979999979166
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software, requiring new approaches to verifying correctness beyond simple output comparisons or statistical accuracy over test datasets. This paper presents a taxonomy for LLM test case design, informed by both the research literature, our experience, and open-source tools that represent the state of practice. We identify key variation points that impact test correctness and highlight open challenges that the research, industry, and open-source communities must address as LLMs become integral to software systems. Our taxonomy defines four facets of LLM test case design, addressing ambiguity in both inputs and outputs while establishing best practices. It distinguishes variability in goals, the system under test, and inputs, and introduces two key oracle types: atomic and aggregated. Our mapping indicates that current tools insufficiently account for these variability points, highlighting the need for closer collaboration between academia and practitioners to improve the reliability and reproducibility of LLM testing.

Related papers

• Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting [0.0]
  Unit testing is essential for verifying the functional correctness of code modules.<n>Unit tests generated by tools that employ traditional approaches, such as search-based software testing (SBST), lack readability, naturalness, and practical usability.<n>Software repositories now include a mix of human-written tests, LLM-generated tests, and those from tools employing traditional approaches such as SBST.
  arXiv  Detail & Related papers  (2026-02-12T18:42:49Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Evaluating Large Language Models on Non-Code Software Engineering Tasks [4.381476817430934]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation.<n>We present the first comprehensive benchmark, which we name Software Engineering Language Understanding' (SELU)<n>SELU covers classification, regression, Named Entity Recognition (NER) and Masked Language Modeling (MLM) targets, with data drawn from diverse sources.
  arXiv  Detail & Related papers  (2025-06-12T15:52:32Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Test Wars: A Comparative Study of SBST, Symbolic Execution, and LLM-Based Approaches to Unit Test Generation [11.037212298533069]
  Large Language Models (LLMs) have opened up new opportunities to generate tests automatically.<n>This paper studies automatic test generation approaches based on three tools: EvoSuite for SBST, Kex for symbolic execution, and TestSpark for LLM-based test generation.<n>Our results show that while LLM-based test generation is promising, it falls behind traditional methods in terms of coverage.
  arXiv  Detail & Related papers  (2025-01-17T13:48:32Z)
• MILE: A Mutation Testing Framework of In-Context Learning Systems [5.419884861365132]
  We propose a mutation testing framework designed to characterize the quality and effectiveness of test data for ICL systems. First, we propose several mutation operators specialized for ICL demonstrations, as well as corresponding mutation scores for ICL test sets. With comprehensive experiments, we showcase the effectiveness of our framework in evaluating the reliability and quality of ICL test suites.
  arXiv  Detail & Related papers  (2024-09-07T13:51:42Z)
• RETAIN: Interactive Tool for Regression Testing Guided LLM Migration [8.378294455013284]
  RETAIN (REgression Testing guided LLM migrAtIoN) is a tool designed explicitly for regression testing in LLM Migrations. Our automatic evaluation and empirical user studies demonstrate that RETAIN, when compared to manual evaluation, enabled participants to identify twice as many errors, facilitated experimentation with 75% more prompts, and achieves 12% higher metric scores in a given time frame.
  arXiv  Detail & Related papers  (2024-09-05T22:22:57Z)
• SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists [59.08999823652293]
  We propose SYNTHEVAL to generate a wide range of test types for a comprehensive evaluation of NLP models. In the last stage, human experts investigate the challenging examples, manually design templates, and identify the types of failures the taskspecific models consistently exhibit. We apply SYNTHEVAL to two classification tasks, sentiment analysis and toxic language detection, and show that our framework is effective in identifying weaknesses of strong models on these tasks.
  arXiv  Detail & Related papers  (2024-08-30T17:41:30Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• On the Evaluation of Large Language Models in Unit Test Generation [16.447000441006814]
  Unit testing is an essential activity in software development for verifying the correctness of software components. The emergence of Large Language Models (LLMs) offers a new direction for automating unit test generation.
  arXiv  Detail & Related papers  (2024-06-26T08:57:03Z)
• 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)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Tasks People Prompt: A Taxonomy of LLM Downstream Tasks in Software Verification and Falsification Approaches [2.687757575672707]
  We develop a novel downstream-task taxonomy to perform classification, mapping, and analysis. The main taxonomy requirement is to highlight commonalities while exhibiting variation points of task types.
  arXiv  Detail & Related papers  (2024-04-14T23:45:23Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• The ICL Consistency Test [14.569770617709073]
  Large language models (LLMs) are adapted to tasks via prompt-based methods like in-context-learning (ICL) This lack of consistency in prompt-based learning hints at a lack of robust generalisation. We here introduce the ICL consistency test -- a contribution to the GenBench collaborative benchmark task (CBT)
  arXiv  Detail & Related papers  (2023-12-08T10:22:43Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)
• How Effective are Large Language Models in Generating Software Specifications? [14.170320751508502]
  Large Language Models (LLMs) have been successfully applied to numerous Software Engineering (SE) tasks. We conduct the first empirical study to evaluate the capabilities of LLMs for generating software specifications from software comments or documentation.
  arXiv  Detail & Related papers  (2023-06-06T00:28:39Z)
• Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models [75.75038268227554]
  Self-Checker is a framework comprising a set of plug-and-play modules that facilitate fact-checking. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments.
  arXiv  Detail & Related papers  (2023-05-24T01:46:07Z)

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.