Literature Search Using AI
The use of artificial intelligence (AI) can simplify the process of searching scientific literature and highlight connections, but it does not replace the expert assessment of quality, context and interpretation.
The Pros and Cons of AI Tools in Finding Literature
At present, AI tools do not offer any significant advantages over traditional database searches. AI cannot assess the relevance of literature to your research topic, nor can it access licensed academic databases. That is why sound research skills remain essential. We offer training sessions and courses to help you acquire these skills.
However, if you possess these skills, AI tools can support your literature search by quickly processing large datasets. AI tools can efficiently analyse large amounts of data, reveal complex relationships and semantically evaluate search queries. The results can often also be automatically presented in summaries
Courses
You can find the latest dates in the events calendar or at the bottom of this page.
Selected AI-Powered Research Tools
- Consensus (partly free, account required)
Search using a research question or keywords - Elicit (partially free, account required)
Search by research question or keywords - Keenious (partly free, account required)
Search using a research question, keywords or an uploaded document - ResearchRabbit (partially free, account required)
Search using a seed paper (a publication you have already found); visually presents connections between publications, authors, etc. - Semantic Scholar (free, no account required)
Search using keywords - Perplexity (free, no account required)
Search using a research question
The Limitations of Literature Research Using AI Tools
Limited Data Set
AI research tools generally rely on freely available data and open-access content. Access to full texts from subscription-based databases, however, is often limited and depends on the respective providers and licensing agreements. For academic literature searches, licensed databases are also highly relevant, as they contain many scholarly publications. As a result, literature searches conducted with AI are not as comprehensive as traditional searches.
Quality Control Required
Tools for literature searches using AI can generate incorrect results in the form of so-called hallucinations, deliver irrelevant results or omit important information. A qualitative review of the results is absolutely essential.
Legal and Data Protection Aspects
The use of AI raises unresolved legal and data protection issues. Neither liability nor the legal handling of the data entered and generated has been conclusively clarified. As you always have to enter your own data when using AI tools, a cautious approach to AI is required.
Choosing Suitable Tools
If you are considering conducting a literature search using AI, it is advisable to use an AI tool that has been specifically developed for literature searches. General language models (Large Language Models, LLM) such as ChatGPT are not yet suitable for systematic literature searches.