인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
Generative large language models (LLMs) promise to reduce researchers’ workload for search, summarization, and drafting, yet their effects across the end-to-end research workflow remain unclear. This study presents a systematic review of 90 empirical studies indexed in Web of Science (2015– 2025) that evaluate LLM assistance in four stages: search, screening, summarizing, and drafting. Following PRISMA guidelines, we coded each study by workflow stage, task type, outcome measures (time and workload, quality and output, user experience), and design and contextual factors such as transparency, prompt structure, user expertise, and organizational setting. Across stages, LLM assistance consistently reduced time and perceived workload, whereas improvements in quality and output were partial and stage-dependent, and user experience was positive but under-measured. We conceptualize LLMs as process productivity accelerators and discuss HCI implications for aligning automation, transparency, and verification mechanisms with task characteristics and organizational context.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-26-02-096523727