arXiv:2611.20033v1 Announce Type: new Abstract: Context: Large Language Models (LLMs) are increasingly embedded in empirical software engineering (ESE) workflows, supporting tasks such as classification, coding, extraction, synthesis, and evaluation. Their probabilistic and opaque behavior, however, introduces methodological concerns that may affect empirical rigor. Aims: This paper investigates threats to validity introduced by LLM-assisted empirical workflows and examines how LLM interactions influence empirical studies. Method: We conducted a secondary analysis of 50 primary studies comprising 69 LLM-assisted research tasks identified through a systematic literature review. We examined the extent to which LLM-related threats were reported, how these threats were characterized, and how they related to established validity dimensions. Results: LLM-related threats remain substantially underreported. We identified recurring threats including classification errors, prompt-dependent interpretation, workflow instability, evaluator bias, downstream propagation of outputs, and model dependence. These threats can affect multiple validity dimensions depending on where and how LLM outputs enter the workflow. Conclusion: We introduce the concept of hidden methodological layer as a conceptual lens for understanding how LLMs influence empirical software engineering workflows. We argue that rigorous LLM-assisted ESE requires making prompts, model configurations, interaction protocols, validation procedures, and downstream reuse of LLM-generated outputs visible as part of the research method.
Continue to arXiv Software Engineering →You are being forwarded in 6s — stay on this page