Dataset Information

The ChatGPT conundrum: Human-generated scientific manuscripts misidentified as AI creations by AI text detection tool.

ABSTRACT: AI Chat Bots such as ChatGPT are revolutionizing our AI capabilities, especially in text generation, to help expedite many tasks, but they introduce new dilemmas. The detection of AI-generated text has become a subject of great debate considering the AI text detector's known and unexpected limitations. Thus far, much research in this area has focused on the detection of AI-generated text; however, the goal of this study was to evaluate the opposite scenario, an AI-text detection tool's ability to discriminate human-generated text. Thousands of abstracts from several of the most well-known scientific journals were used to test the predictive capabilities of these detection tools, assessing abstracts from 1980 to 2023. We found that the AI text detector erroneously identified up to 8% of the known real abstracts as AI-generated text. This further highlights the current limitations of such detection tools and argues for novel detectors or combined approaches that can address this shortcoming and minimize its unanticipated consequences as we navigate this new AI landscape.

SUBMITTER: Rashidi HH

PROVIDER: S-EPMC10727991 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The ChatGPT conundrum: Human-generated scientific manuscripts misidentified as AI creations by AI text detection tool.

Rashidi Hooman H HH Fennell Brandon D BD Albahra Samer S Hu Bo B Gorbett Tom T

Journal of pathology informatics 20231017

AI Chat Bots such as ChatGPT are revolutionizing our AI capabilities, especially in text generation, to help expedite many tasks, but they introduce new dilemmas. The detection of AI-generated text has become a subject of great debate considering the AI text detector's known and unexpected limitations. Thus far, much research in this area has focused on the detection of AI-generated text; however, the goal of this study was to evaluate the opposite scenario, an AI-text detection tool's ability t ...[more]

PMID: 38116171

Similar Datasets

Project description:BackgroundArtificial intelligence (AI) has many applications in various aspects of our daily life, including health, criminal, education, civil, business, and liability law. One aspect of AI that has gained significant attention is natural language processing (NLP), which refers to the ability of computers to understand and generate human language.ObjectiveThis study aims to examine the potential for, and concerns of, using AI in scientific research. For this purpose, high-impact research articles were generated by analyzing the quality of reports generated by ChatGPT and assessing the application's impact on the research framework, data analysis, and the literature review. The study also explored concerns around ownership and the integrity of research when using AI-generated text.MethodsA total of 4 articles were generated using ChatGPT, and thereafter evaluated by 23 reviewers. The researchers developed an evaluation form to assess the quality of the articles generated. Additionally, 50 abstracts were generated using ChatGPT and their quality was evaluated. The data were subjected to ANOVA and thematic analysis to analyze the qualitative data provided by the reviewers.ResultsWhen using detailed prompts and providing the context of the study, ChatGPT would generate high-quality research that could be published in high-impact journals. However, ChatGPT had a minor impact on developing the research framework and data analysis. The primary area needing improvement was the development of the literature review. Moreover, reviewers expressed concerns around ownership and the integrity of the research when using AI-generated text. Nonetheless, ChatGPT has a strong potential to increase human productivity in research and can be used in academic writing.ConclusionsAI-generated text has the potential to improve the quality of high-impact research articles. The findings of this study suggest that decision makers and researchers should focus more on the methodology part of the research, which includes research design, developing research tools, and analyzing data in depth, to draw strong theoretical and practical implications, thereby establishing a revolution in scientific research in the era of AI. The practical implications of this study can be used in different fields such as medical education to deliver materials to develop the basic competencies for both medicine students and faculty members.

Project description:IntroductionChatGPT, a sophisticated large language model (LLM), has garnered widespread attention for its ability to mimic human-like communication. As recent studies indicate a potential supportive role of ChatGPT in academic writing, we assessed the LLM's capacity to generate accurate and comprehensive scientific abstracts from published Randomised Controlled Trial (RCT) data, focusing on the adherence to the Consolidated Standards of Reporting Trials for Abstracts (CONSORT-A) statement, in comparison to the original authors' abstracts.MethodologyRCTs, identified in a PubMed/MEDLINE search post-September 2021 across various medical disciplines, were subjected to abstract generation via ChatGPT versions 3.5 and 4, following the guidelines of the respective journals. The overall quality score (OQS) of each abstract was determined by the total number of adequately reported components from the 18-item CONSORT-A checklist. Additional outcome measures included percent adherence to each CONOSORT-A item, readability, hallucination rate, and regression analysis of reporting quality determinants.ResultsOriginal abstracts achieved a mean OQS of 11.89 (95% CI: 11.23-12.54), outperforming GPT 3.5 (7.89; 95% CI: 7.32-8.46) and GPT 4 (5.18; 95% CI: 4.64-5.71). Compared to GPT 3.5 and 4 outputs, original abstracts were more adherent with 10 and 14 CONSORT-A items, respectively. In blind assessments, GPT 3.5-generated abstracts were deemed most readable in 62.22% of cases which was significantly greater than the original (31.11%; P = 0.003) and GPT 4-generated (6.67%; P<0.001) abstracts. Moreover, ChatGPT 3.5 exhibited a hallucination rate of 0.03 items per abstract compared to 1.13 by GPT 4. No determinants for improved reporting quality were identified for GPT-generated abstracts.ConclusionsWhile ChatGPT could generate more readable abstracts, their overall quality was inferior to the original abstracts. Yet, its proficiency to concisely relay key information with minimal error holds promise for medical research and warrants further investigations to fully ascertain the LLM's applicability in this domain.

Dataset Information

The ChatGPT conundrum: Human-generated scientific manuscripts misidentified as AI creations by AI text detection tool.

Publications

The ChatGPT conundrum: Human-generated scientific manuscripts misidentified as AI creations by AI text detection tool.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets