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

• 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)
• 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)
• 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)
• 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.