Automated reproducibility assessments in the social and behavioral sciences using large language models
English summary
A study proposes a framework that employs large language models to automate the assessment of research reproducibility in the social and behavioral sciences. The framework aims to reduce time, effort, and human biases associated with manual reproducibility checks. By leveraging LLMs, the method can streamline the evaluation of whether study results can be reliably reproduced. This innovation addresses the ongoing replicability crisis in these fields, potentially fostering more transparent and trustworthy research practices. The paper discusses the technical approach and its implications for improving scientific credibility.
Chinese summary
一项研究提出了利用大语言模型自动评估社会科学与行为科学领域研究可重复性的框架。该框架旨在减少人工检查所需的时间、精力和人为偏见。通过利用大语言模型，该方法可简化对研究结果是否可被可靠复现的评估。这一创新回应了这些领域中持续存在的可重复性危机，有望促进更透明、更可信的研究实践。论文讨论了技术方法及其对提升科学可信度的意义。
Key points
A novel framework uses LLMs to automate reproducibility assessments in social and behavioral sciences.
提出新框架，利用大语言模型自动进行社会科学与行为科学的可重复性评估。
The automation reduces manual effort and mitigates human biases in judging replicability.
自动化减少了人工工作量，并减少了在判断可复制性时的人为偏见。
The approach targets the replicability crisis by making reproducibility checks more efficient and objective.
该方法通过使可重复性检查更高效、更客观，应对可复制性危机。