AI evidence extraction

Introduction to generative artificial intelligence tools for academic article writing

Joon Seo Lim · Science Editing · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

3/4

Quality (LMQS)

Evidence

Citations

8.72

FWCI

Top 10%

Impact

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.6087/kcse.393

Methodology & findings

Study design

Narrative review and instructional guide.

Primary method

No formal statistical methods employed. The paper references one survey statistic (69.4% and 51.2%) but provides no confidence intervals or statistical testing.

Main result

The paper finds that "69.4% of researchers in the natural sciences and 51.2% of those in the medical field use generative AI for academic purposes at least once a month," and identifies multiple AI tools across literature search, article organization, and manuscript writing stages. The paper states that "Modern AI tools extend beyond simple text generation and now offer advanced capabilities, including literature network analysis, identification of research gaps, and prediction of emerging research trends."

Reports effect sizes.

Research paradigm

Interpretivist/Descriptive

Author conclusions

The authors conclude that "Regardless of which AI tools are used, the requirements for article submission remain unchanged. Authors must disclose which AI tools were used in the cover letter and manuscript, typically in the methods section or acknowledgments, and they bear full responsibility for the accuracy of the content." They emphasize that "research workflows and outcomes can become noticeably more efficient and smoother than in the pre-AI era" when proper protocols are followed, noting that "Researchers must continue to develop their own expertise to ensure that human judgment remains the gold standard throughout all stages of research."

Risk of bias

Selection bias in tool coverage: unclear if all relevant AI tools are included or if selection is based on author familiarity; Publication bias: information may be skewed toward higher-profile or more widely-known tools; No systematic evaluation of tool accuracy or reliability across different use cases; Limited discussion of tool limitations beyond general caveats

Limitations

The paper acknowledges that "most tools are optimized for English-language publications, research published in other languages may be underrepresented" and that researchers "should always manually verify the accuracy of AI-generated information, particularly citation details and statistical results, by consulting original source materials." Additionally, the paper notes that "hallucinations are common in citation recommendations" when using general LLMs, and that "reliance on a single tool should be avoided."

Open questions raised

The authors identify the need for researchers to continue developing expertise and maintaining critical appraisal skills, noting that "Continued engagement with traditional literature searches through PubMed and Google Scholar is necessary to maintain critical appraisal skills" and that "it is essential to remember that AI tools assist but do not replace a researcher's judgment."
The paper does not explicitly identify specific research gaps but emphasizes ongoing needs: (1) continued manual verification of AI-generated information; (2) need for deeper understanding through manual article reading rather than excessive automation; (3) importance of maintaining traditional literature search skills through PubMed and Google Scholar to preserve critical appraisal abilities.
The paper identifies the need for researchers to verify AI-generated information against original sources, particularly for citation details and statistical results. It also highlights the gap that most AI tools are optimized for English-language publications, leaving non-English research underrepresented.

Data: Notion article database template; Author's Notion article database template (read-only format): https://charm-serpent-80c.notion.site/DB-1edae5f4278c805a988fe9207061b329; Author's Notion article database templateExtracted from: pdfAgreement 76%

Explore related topics

AI Manuscript Writing Academic Writing Literature Review