Despite the rapid advancements in large language models (LLMs), human researchers still hold the edge in crafting trustworthy systematic reviews. A recent study published in the journal Scientific Reports reveals that human expertise remains indispensable for producing rigorous systematic literature reviews, with LLMs serving best as supervised support tools rather than independent authors. The study, titled 'Human researchers are superior to large language models in writing a medical systematic review in a comparative multitask assessment', highlights the limitations of LLMs in key tasks such as literature search, data summarization, and final manuscript drafting. However, LLMs demonstrated time-effectiveness in initial literature screening, alongside human researchers' cross-search of databases and references. The research underscores the need for prompt-engineering strategies and guided prompting to enhance LLM performance, while also emphasizing the critical role of human expertise in evidence-based medicine.
