Search-based Selection of Metamorphic Relations for Optimized Robustness Testing of Large Language Models
Reviewed by Pithpith:QZGFNDMCopen to challenge →
read the original abstract
Assessing the trustworthiness of Large Language Models (LLMs), such as robustness, has garnered significant attention. Recently, metamorphic testing that defines Metamorphic Relations (MRs) has been widely applied to evaluate the robustness of LLM executions. However, the MR-based robustness testing still requires a scalable number of MRs, thereby necessitating the optimization of selecting MRs. Most extant LLM testing studies are limited to automatically generating test cases (i.e., MRs) to enhance failure detection. Additionally, most studies only considered a limited test space of single perturbation MRs in their evaluation of LLMs. In contrast, our paper proposes a search-based approach for optimizing the MR groups to maximize failure detection and minimize the LLM execution cost. Moreover, our approach covers the combinatorial perturbations in MRs, facilitating the expansion of test space in the robustness assessment. We have developed a search process and implemented four search algorithms: Single-GA, NSGA-II, SPEA2, and MOEA/D with novel encoding to solve the MR selection problem in the LLM robustness testing. We conducted comparative experiments on the four search algorithms along with a random search, using two major LLMs with primary Text-to-Text tasks. Our statistical and empirical investigation revealed two key findings: (1) the MOEA/D algorithm performed the best in optimizing the MR space for LLM robustness testing, and (2) we identified silver bullet MRs for the LLM robustness testing, which demonstrated dominant capabilities in confusing LLMs across different Text-to-Text tasks. In LLM robustness assessment, our research sheds light on the fundamental problem for optimized testing and provides insights into search-based solutions.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Minimum Complete MR Subsets under Semantic-Mutation Fault Models: A Support-Set Domination Boundary
The paper establishes a support-set domination boundary governed by kill-signature heterogeneity that separates when class-level MR abstraction suffices from when mutant-level minimization is required, proving the Min...
-
Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey
A systematic survey of 93 studies that maps the bidirectional relationship between metamorphic testing and LLMs, proposing a taxonomy for MT applied to LLMs and LLMs applied to MT.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.