Logo of the University of Passau

Preparation Phase

General AI Assistants can substantially facilitate the early stages of literature searching. They support the structuring and refinement of research ideas, help identify potential research gaps, and contribute to the development of a precise research question.

They also generate suitable keywords, including synonyms and broader conceptual terms, which enhances the systematic and efficient development of search strategies. Furthermore, by explaining technical terminology, contextualizing historical developments, or simplifying complex theoretical concepts, AI Assistants help close knowledge gaps and strengthen the conceptual foundation for conducting a literature review.

General AI Assistants include, among others:

The precise formulation of Prompts is crucial for achieving effective results.

Tips for Effective Prompting

A well‑crafted prompt is essential for obtaining meaningful results from an AI system.

The more clearly and logically you formulate your instruction, the more effectively the AI can search and produce relevant outputs. Depending on the context of use, this includes defining the disciplinary background, the time frame, and the key search criteria, as well as specifying the intended audience, the preferred style, and the desired format. Providing concrete details helps prevent vague or overly broad responses.

The iterative process is especially important: test different phrasings, ask for feedback, and gradually refine your prompts.

In this way, you can minimize AI weaknesses such as inaccurate answers or hallucinations and achieve the best possible results.

1. Define Your Goal

  • Before formulating a prompt, you should know exactly what you want to achieve. Are you looking for a summary, an analysis, or creative content?
  • Clear intentions guide the AI to deliver better results.

2. Provide a Precise Initial Instruction

  • Avoid vague phrasing.
  • Instead of "Tell me something about artificial intelligence," write: "Name three current research trends in AI-powered literature search."

3. Specify the Target Audience

  • Should the response be written for experts, students, or a general readership?
  • Example: “Explain the term ‘Large Language Models’ in simple words for first‑semester students.”

4. Define the Language and Writing Style

  • Do you want the response to be neutral, academic, or more informal?
  • Example: “Summarize the study in an academic tone” or “Explain it as if you were telling it to a fellow student.”

5. Clarify Your Preferred Format

  • Should the response be structured as a list, table, paragraph, or follow a specific citation style?
  • Example: "Provide the key points as a numbered bullet list."

6. Add Key Details

  • Include background information, examples, or constraints.
  • Example: "Compare Müller's (2022) and Schmidt's (2023) studies, focusing specifically on methodology."

7. Assign a Role to the AI

  • Sometimes it helps to frame the system within a specific perspective.
  • Example: "Respond as a literature scholar writing a research paper on AI in philology."

8. Refine the Prompt Step by Step

  • The first prompt rarely produces the perfect result. Ask the AI for feedback on your previous inputs and request clarification on any ambiguities or misunderstandings. At the same time, regularly provide feedback to the model to refine or realign responses.
  • Example: “The initial points were too general, now go into more detail.”

Contact

Anja Richter

Anja Richter

Teaching Librarian for AI Literacy

Anja.Richter@uni-passau.de

I agree that a connection to the Vimeo server will be established when the video is played and that personal data (e.g. your IP address) will be transmitted.
I agree that a connection to the YouTube server will be established when the video is played and that personal data (e.g. your IP address) will be transmitted.
Show video