A Software Engineering Perspective on Testing Large Language Models: Research, Practice, Tools and Benchmarks

TL;DR

This paper reviews the current state of testing Large Language Models (LLMs) from a Software Engineering perspective, focusing on tools, benchmarks, and research to ensure their reliability in safety-critical applications.

Contribution

It introduces a taxonomy of LLM testing topics and maps existing research, tools, and benchmarks onto this framework to identify gaps and guide future work.

Findings

Existing tools and benchmarks are mapped to the taxonomy.

Gaps in research and practice are identified for future focus.

The paper promotes better communication between practitioners and researchers.

Abstract

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. Software Engineering (SE) research on testing Machine Learning (ML) components and ML-based systems has systematically explored many topics such as test input generation and robustness. We believe knowledge about tools, benchmarks, research and practitioner views related to LLM testing needs to be similarly organized. To this end, we present a taxonomy of LLM testing topics and conduct preliminary studies of state of the art and practice approaches to research, open-source tools and benchmarks for LLM testing, mapping results onto this taxonomy. Our goal is to identify gaps requiring more research and engineering effort and inspire a clearer communication between LLM practitioners and the SE research community.