Generative AI applications such as ChatGPT, Microsoft Copilot, Google Gemini and Claude can be used in information retrieval, but they cannot replace thorough information search. Below, we explain what they can and should be used to help you search for information. 
-
Orientation to the topic
- You can use generative AI applications as a source of inspiration when brainstorming and formulating your research question. Be aware that they may introduce biased assumptions into the discussion. Remember that they may not have information on the latest research findings.
- Not all data producers provide their data to AI applications, which is another reason why the data used by the applications is incomplete.
-
Planning your search
- Generative AI can help you find good keywords for your information search. It is worth asking the AI to complete its list of search terms several times, rather than settling for the first answer. Please note, however, that this does not replace the need to consult glossaries and check the terms used by experts in the field.
- AI can help you identify tools or databases that are relevant to your topic. Please note that it may not provide a comprehensive answer from the available sector-specific databases. Nor can it tell you whether our library subscribes to a particular database. For comprehensive information on sectoral and cross-sectoral data sources, please consult the Library's Databases A-Z list.
- Please note that AI applications are not trained to formulate search phrases for the purpose of searching for scientific information. If you ask it to construct search phrases for you, you might probably have to edit and reformat them.
-
Conducting a search in a database
- Generative AI cannot help you with your actual search for information. It cannot search for information in a systematic and transparent way.
- AI applications can tell you how the database works. However, we recommend that you check the manual directly with the database of your choice. The functionality may have changed, and the response may well be out of date.
-
Evaluation of search results
- You cannot use generative AI applications to evaluate search results. Information evaluation is a human skill based on criteria that you yourself consider relevant. As a researcher or student, as a data seeker, you have to decide whether a source is relevant to your work.
- However, you can use these applications to clarify and translate difficult texts, as it is good for summarising or reformatting text. However, remember to be critical of sources, i.e. don't believe everything, AI may present biased views.
-
References and citations
- Generative AI applications are unable to reliably provide sources for the texts they write. They can provide a bibliography when requested, but the sources may be incorrect or completely fabricated. If an AI tool gives you a reference to an article you want to use in your research, it's important to make sure that the source exists and get it for you to read. You can check the existence of publications, e.g. Andor search service and Google Scholar.
- AI applications are also unable to create bibliographies using certains citation styles. Reference management software, like Zotero and others, support a myriad of citation styles and are good tools for this purpose.
When using AI applications, always consider how they handle the data you enter. As a general rule, all data input to AI services is stored outside the EU/EEA and cannot be deleted from there. For example, no personal data, business secrets, confidential information or sensitive information may be entered into the services.
Instructions (Häme University of Applied Sciences) on how to restrict the use of your input for AI training in ChatGPT.
