跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20033 · v1

The Hidden Methodological Layer: Uncovering Threats to Validity in LLM-Assisted Empirical Software Engineering

首次提交 2026-11-15 22:24
版本更新 2026-11-15 22:24
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 22:24 · 最新观测版本

The Hidden Methodological Layer: Uncovering Threats to Validity in LLM-Assisted Empirical Software Engineering

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.

查看此版本解读 →查看此版本原文 ↗