TY  - JOUR
AU  - Mugaanyi, Joseph
AU  - Cai, Liuying
AU  - Cheng, Sumei
AU  - Lu, Caide
AU  - Huang, Jing
PY  - 2024
DA  - 2024/4/5
TI  - Evaluation of Large Language Model Performance and Reliability for Citations and References in Scholarly Writing: Cross-Disciplinary Study
JO  - J Med Internet Res
SP  - e52935
VL  - 26
KW  - large language models
KW  - accuracy
KW  - academic writing
KW  - AI
KW  - cross-disciplinary evaluation
KW  - scholarly writing
KW  - ChatGPT
KW  - GPT-3.5
KW  - writing tool
KW  - scholarly
KW  - academic discourse
KW  - LLMs
KW  - machine learning algorithms
KW  - NLP
KW  - natural language processing
KW  - citations
KW  - references
KW  - natural science
KW  - humanities
KW  - chatbot
KW  - artificial intelligence
AB  - Background: Large language models (LLMs) have gained prominence since the release of ChatGPT in late 2022. Objective: The aim of this study was to assess the accuracy of citations and references generated by ChatGPT (GPT-3.5) in two distinct academic domains: the natural sciences and humanities. Methods: Two researchers independently prompted ChatGPT to write an introduction section for a manuscript and include citations; they then evaluated the accuracy of the citations and Digital Object Identifiers (DOIs). Results were compared between the two disciplines. Results: Ten topics were included, including 5 in the natural sciences and 5 in the humanities. A total of 102 citations were generated, with 55 in the natural sciences and 47 in the humanities. Among these, 40 citations (72.7%) in the natural sciences and 36 citations (76.6%) in the humanities were confirmed to exist (P=.42). There were significant disparities found in DOI presence in the natural sciences (39/55, 70.9%) and the humanities (18/47, 38.3%), along with significant differences in accuracy between the two disciplines (18/55, 32.7% vs 4/47, 8.5%). DOI hallucination was more prevalent in the humanities (42/55, 89.4%). The Levenshtein distance was significantly higher in the humanities than in the natural sciences, reflecting the lower DOI accuracy. Conclusions: ChatGPT’s performance in generating citations and references varies across disciplines. Differences in DOI standards and disciplinary nuances contribute to performance variations. Researchers should consider the strengths and limitations of artificial intelligence writing tools with respect to citation accuracy. The use of domain-specific models may enhance accuracy. 
SN  - 1438-8871
UR  - https://www.jmir.org/2024/1/e52935
UR  - https://doi.org/10.2196/52935
UR  - http://www.ncbi.nlm.nih.gov/pubmed/38578685
DO  - 10.2196/52935
ID  - info:doi/10.2196/52935
ER  -