On the Impact of Requirements Smells in Prompts: The Case of Automated Traceability

TL;DR

This study examines how requirements smells, indicators of issues like ambiguity, influence the performance of large language models in generating software traceability links, revealing mixed effects depending on the task.

Contribution

It is the first to analyze the impact of requirements smells on LLM-based traceability tasks, providing insights into when these issues affect model performance.

Findings

Requirements smells slightly affect trace link prediction accuracy.

No significant impact of requirements smells on code tracing tasks.

Highlights need for guidelines to mitigate issues caused by requirements smells.

Abstract

Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central role in shaping the input prompts that guide LLMs, as they are often used as part of the prompts to synthesize the artifacts. However, the impact of requirements formulation on LLM performance remains unclear. In this paper, we investigate the role of requirements smells-indicators of potential issues like ambiguity and inconsistency-when used in prompts for LLMs. We conducted experiments using two LLMs focusing on automated trace link generation between requirements and code. Our results show mixed outcomes: while requirements smells had a small but significant effect when predicting whether a requirement was implemented in a piece of code (i.e., a trace link exists), no significant effect was observed when tracing the requirements with the associated lines of code. These findings suggest that requirements smells can affect LLM performance in certain SE tasks but may not uniformly impact all tasks. We highlight the need for further research to understand these nuances and propose future work toward developing guidelines for mitigating the negative effects of requirements smells in AI-driven SE processes.