Teaching Library

AI tools can generate factually incorrect information or fabricated sources – so-called ‘hallucinations’ – which is why every output must be critically scrutinised. There is a risk of research misconduct if AI-generated content is used without attribution or presented as one’s own work. Furthermore, data protection issues may arise if unpublished research data or personal information is entered into external systems. Another methodological problem is that AI models do not carry out genuine source criticism and may reproduce biases present in the training data.

Recommendation: Use AI tools to complement traditional research tools – not as a replacement!

The following tools make it easier to get started with your research by helping you identify topics and formulate research questions. They suggest relevant subject areas and questions, thereby helping you to begin the research process in a focused manner. They are well suited for creating outlines and for assisting with the identification of keywords for your literature search.

• ChatGPT

ChatGPT can support you with literature research in an academic context by structuring topics, explaining key concepts and refining research questions. It also helps you to formulate, revise and structure seminar papers or research proposals, as well as summarise complex specialist texts. In addition, it can explain methodological approaches or provide guidance on programming-related issues.

• Claude AI

Claude AI primarily supports you by analysing and summarising complex academic texts, PDFs and datasets, which significantly speeds up your literature search. It helps with structuring papers, brainstorming research questions and formulating academic texts by optimising drafts or adapting them stylistically. Thanks to the large context windows, entire papers can be uploaded to receive feedback on logic, argumentation or citation styles. The tool helps you identify similarities and contradictions between multiple sources.

• Copilot

Copilot efficiently supports you with literature reviews by finding relevant studies, creating summaries and helping to structure complex topics. In Microsoft, it can create drafts for essays or presentations in Word and PowerPoint, optimise texts and format references. The AI assistant also helps you understand difficult academic texts by explaining concepts and suggesting structured outlines.

• Le Chat Mistral

Le Chat Mistral is a European alternative to well-known AI tools and is GDPR-compliant. As well as being used for research and structuring academic work, Mistral’s Le Chat excels at data analysis. For example, it can execute Python code to clean up datasets, carry out statistical analyses and create visualisations.

• Lumo (Proton)

This data-protection-compliant AI assistant (zero-access encryption) is particularly suitable for higher education, as conversations are not stored or used to train the models. This is ideal for handling sensitive research data or unpublished manuscripts. Lumo supports you by helping to analyse, summarise and organise research documents. The ability to upload documents such as PDFs and organise them into ‘projects’ allows complex academic texts to be processed efficiently.

• Perplexity

Perplexity.ai supports you in your studies through AI-powered, citation-based research that directly provides reliable sources and specialist academic literature. In the special ‘Academic’ mode, you can clarify research questions, have literature summarised clearly and get to grips with complex topics more quickly. The tool also helps with structuring papers, brainstorming and analysing studies by uploading documents.

• Consensus

Consensus supports you by using AI to search directly through over 200 million peer-reviewed academic publications for answers and summarising them clearly. You can ask complex research questions and receive evidence-based results with direct quotations, which significantly speeds up literature research for seminar papers or dissertations. The tool also helps you to identify scientific consensus on a topic, compare methodologies and export citations correctly. 

• Elicit

Elicit supports you with your seminar paper or bachelor’s/master’s thesis by using AI to find relevant literature via semantic search, even without exact keywords. It automatically analyses and summarises research papers, methodologies and results, enabling you to save up to 80 per cent of the time spent on literature searches and reviews. The tool also extracts specific data from papers, creates comparison tables and helps you explore research questions. 

• ORKG ask

ORKG ask supports you in your academic work by using AI to extract targeted answers to complex research questions from over 80 million scientific publications. It enables semantic searching that goes beyond simple keywords and helps you gain a quicker overview of the state of the art in research. The tool also simplifies literature management through integrated export functions and helps you compare research papers across disciplinary boundaries. 

• SciSpace

SciSpace supports you with an AI-powered platform that enables you to search through, understand and summarise scientific literature more quickly. The ‘Copilot’ feature allows you to highlight complex papers, equations or tables and have them explained directly in your browser, which is particularly helpful for literature reviews. You can also upload your own work, use paraphrasing tools to aid your writing, and generate citations automatically. 

• Scopus AI

Scopus AI supports you in your academic work by answering complex research questions in natural language through analysis of the Scopus database and by accurately summarising relevant literature. It makes it easier to get to grips with new topics, identifies research gaps and key literature, and visualises connections between different fields of research. It also helps to reduce research time by providing reliable summaries based on verified content. 

Access for external users

• Semantic Scholar

Semantic Scholar supports your studies through an AI-powered literature search that scans over 200 million academic papers and efficiently highlights the most relevant sources. Thanks to features such as ‘TLDR’ summaries (Too Long; Didn’t Read) and the analysis of citation networks, you can understand content more quickly and identify important research papers. Furthermore, personal libraries, Zotero integration and “Research Feeds” allow you to organise your literature searches and keep them up to date at all times. 

• ChatGPT

As an AI writing tool, ChatGPT is particularly effective at helping to structure work, formulate complex research questions and overcome writer’s block by generating draft outlines. As a writing assistant, it also helps to paraphrase academic texts, improve their style, check for errors and format the reference list. It can also provide feedback on first drafts, making the writing process more efficient. 

• Grammarly

Grammarly supports you by checking English-language texts in real time for grammar, spelling, punctuation and style, to improve clarity and precision. In addition, the integrated plagiarism checker and suggestions for a more formal tone help you to meet academic standards and present your work professionally. It is a valuable tool for refining your own writing style and overcoming language barriers.

A writing assistant that focuses on grammar correction, spell-checking and tone optimisation.

• Jasper 

Jasper is particularly helpful in quickly creating outlines, formulating precise paragraphs and overcoming writer’s block. It helps maintain an academic tone, rephrase sentences and structure texts in terms of content, making the entire writing process more efficient. Furthermore, the use of document workflows enables longer texts to be written consistently. The tool also offers features such as plagiarism detection and formatting assistance.

• Neuroflash (D)

Neuroflash supports you in particular through AI-based structuring and phrasing of texts, by helping to optimise academic writing style or create outlines. Features such as ‘rewrite’ and ‘continue writing’ enable complex topics to be expressed more precisely and in the appropriate tone (academic/factual). In addition, the document editor allows you to develop drafts more quickly, making the writing process – for example, when working on seminar papers or dissertations – more efficient.

AI tools can make your work considerably easier and assist you with your academic literature research. However, the quality of the results depends heavily on a precise input, known as a prompt. The clearer and more detailed your prompt is, the better the AI’s response will be. Only with the right prompt can the full potential of AI be realised.

A good prompt is precise and clear, contextualised and formulated with a specific aim in mind! 

It minimises room for interpretation, precisely defines the objective and framework, and explicitly states quality requirements.

Prompting tips 

1. Define the role – Specify the role in which the AI model should respond

   Example: Act as a professor of mechanical engineering specialising in thermodynamics

2. Provide context – Describe the framework conditions such as the degree programme, level, objective or project scope

   Example: The text is for a seminar paper in the 5th semester of a Bachelor’s degree in Mechanical Engineering at a technical university.

3. Narrow down the specific topic – Formulate the topic clearly and specifically

   Example: Topic: Comparison of the efficiency of heat pump systems in industrial applications.

4. Define the objective and expected output – Specify exactly what you need (e.g. outline, analysis, literature review)

   Example: Create a structured outline with brief explanations of the content for each section.

5. Specify the format and scope – Determine the structure, length, citation style or presentation format

   Example: Length: approx. 800 words, factual academic style, with bullet points and clear section headings.

6. Formulate quality criteria and restrictions – Define methodological requirements or limitations

   Example: Take current technological developments into account, cite typical key figures and highlight possible limitations. No speculative statements.

Example prompt:

Assume the role of a professor of mechanical engineering specialising in thermodynamics.
The text is for a seminar paper in the 5th semester of a Bachelor’s degree in Mechanical Engineering at a technical university.
The topic is a comparison of the efficiency of heat pump systems in industrial applications.
Create a structured outline with brief technical explanations for each section.
Approximately 800 words in length, written in a factual, academic style with clear headings.
Take into account relevant performance indicators (e.g. COP, annual performance factor), current technological developments, and technical and economic limitations.

Reusing the video

It is important to note that:

• credit must always be given.
• the video must not be altered.
• the video must not be used for commercial purposes.

• the following licence information is observed: 

  Video ‘The Library That Turns People into Crazy Research Pros’ by Jonas Ludäscher, Tamara Schmidt, Verena Stemmer, Finn Armistead and Ruben Schlag (all from Ingolstadt University of Technology) under the CC BY-ND-NC 4.0 licence via https://doi.org/10.5281/zenodo.19052030