gKI Anwendungen in der Lehre

werden auf große Mengen von Inhalten trainiert. Daher können sie vorhersagen, welches Wort als nächstes in geschriebenem Text kommen sollte, ähnlich wie die Autovervollständigungsfunktion in Suchleisten. Wenn Sie einen Prompt (eine Texteingabe) eingeben, versucht das LLM den Prompt auf der Grundlage seines Trainings logisch zu erweitern. Dadurch sind LLM in der Lage, viele Aufgaben in vielen Bereichen zu erfüllen. Es gibt jedoch keine Bedienungsanleitung dafür, so dass es nicht immer ersichtlich ist, welche Aufgaben gut oder weniger gut erledigt werden. Weil LLM kein wirkliches Verständnis haben, machen sie auch Fehler. Es liegt also in der Verantwortung der Nutzenden, alle Ergebnisse zu überprüfen.

„10 Fragen zu KI-Output, Urheberrecht und OER“ - eine Broschüre zu Urheberrechtsfragen bei der Verwendung KI-generierter Inhalte. Autorin ist Andrea Schlotfeldt, Juristin an der HAW Hamburg.

1. Ist eine Antwort unklar oder verwirrend, bitten Sie um weitere Erklärungen, Beispiele oder eine andere Formulierung. Fragen Sie solange nach, bis Sie das gewünschte Ergebnis erhalten.

2. Interagieren Sie dazu auf natürliche Weise mit der gKI, stellen Sie Fragen und widersprechen Sie den Antworten - so wie Sie es auch mit einem menschlichen Gesprächspartner tun würden.

1. Die gKI kann besser antworte, wenn sie weiß, wo Sie Probleme haben. Je mehr Kontext Sie ihr geben, desto wahrscheinlicher ist es, dass sie Ihnen helfen kann.
2. Oft hilft es, der KI eine Rolle zuzuweisen: „Sie sind ein freundlicher Lehrer, der Studenten in Einführungskursen wirtschaftliche Konzepte erklärt“, zum Beispiel.

1. Gehen Sie nicht davon aus, dass die gKI das Gespräch verfolgt. LLMs haben ein "begrenztes Gedächtnis"
2. Wenn der Überblick in den Antworten verloren geht erinnern Sie mit Eingaben daran, was Sie wissen möchten, und stellen Sie weitere Fragen.

Sind Sie an Prompting in der Hochschullehre interessiert?

Das Hochschulforum Digitalisierung (HFD) und der KI-Campus bieten in Zusammenarbeit mit Expert:innen im Rahmen des ‚Prompt-Labors‘ einen umfangreichen Experimentierraum für Hochschulangehörige.

Im Prompt-Labor haben Teilnehmende Zugang zu verschiedenen Selbstlernmaterialien.

Ein Katalog erprobter Prompts aus Anwendungskontexten im Bereich der Hochschullehre.

Der Katalog wurde eingerichtet im Rahmen des Prompt-Labor: Generative KI in der Hochschullehre⁠, veranstaltet von Hochschulforum Digitalisierung und KI-Campus – die Lernplattform für Künstliche Intelligenz im Stifterverband⁠. Alle freigegebenen Prompts werden als OER unter der CC BY SA 4.0 Lizenz veröffentlicht. Bitte bei Weiterveröffentlichungen den Namen der Autoren, den Link zum Prompt-Labor und den Lizenzhinweis angeben.⁠

Kontakt: Stefan Göllner (stefan.goellner@stifterverband.de).

Prompt Library, offered by AI for Education. A variety of prompts to help you lesson plan and do administrative tasks with GenAI chatbots.

KI kann "lügen" und plausibel klingende, aber falsche Informationen produzieren. Prüfen Sie erhaltene Ergebnisse vor der Weiterverwendung.

In Abhängigkeit von den Trainingsdaten können Ergebnisse Voreingenommenheiten oder Vorurteile enthalten. Ziehen Sie stets weitere Informationsquellen hinzu.

Wenn Daten in LLM eingegeben werden, könnten sie für zukünftiges Training verwendet werden. Der aktuelle Stand des Datenschutzes bleibt für viele Modelle unklar, und die rechtlichen Auswirkungen sind oft ungewiss. Teilen Sie LLM nichts mit, was Sie privat halten möchten.

Schleifen / "Steckenbleiben": Die Antworten können sich wiederholen bzw. ganz zum Erliegen kommen. Versuchen Sie es später mit einer neuen Eingabe oder nutzen SIe ggfs. ein anderes LLM.

KI ist unberechenbar. Aufgrund einer rieseigen menge an Trainingsdaten versucht ein LLM, Ihren Prompt zu erfüllen oder vernünftig zu beantworten. Aberes ist unvorhersehbar, was herauskommen wird. Auf ein und dieselbe Aufforderung kann ein LLM bei jeder Anwendung völlig anders reagieren. Das bedeutet, dass Ihre Mitmenschen möglicherweise unterschiedliche Antworten erhalten, ebenso wie Sie selbst, wenn Sie die Aufforderung mehr als einmal ausprobieren.

Prüfen Sie alle Ergebnisse, die LLM liefern, bevor Sie sie weitergeben / damit weiterarbeiten. Sichern Sie sich ab über die Nutzung weiterer Quellen oder Ihr Fachwissen. Rechtlich ist eine gKI keine Person und damit nicht für seine Ergebnisse haftbar - Sie aber schon, sowohl bei der Eingabe des Prompts als auch bei der Verwendung der Ergebnisse.

Sehen Sie hier einige Empfehlungen, wie Sie damit in Ihrem Lehralltag Fallstricke umgehen und das Potenzial von gKI vorteilhaft nutzen können.

^{Quelle: https://hbsp.harvard.edu/inspiring-minds/student-use-cases-for-ai, übersetzt mit DeepL}

Erfahren Sie mehr dazu: Student Use Cases for AI by Ethan Mollick and Lilach Mollick, Sept. 2023

Sammlung von Informationen zu KI mit kurzer Kommentierung der Links zur besseren Orientierung (gesammelt und kommentiert von H. Mersmann-Hoffmann, Sprachenzentrum der Uni Münster). Keine Verantwortung für den Inhalt von Links. CC BY NC SA 28.04.2025

Von Heike Mersmann-Hoffmann

Enthält Zusammenfassungen und Challenges für verschiedene Bereiche der Lehre:

- KI, Digitale Lehre + Medien, Motivation, Prüfungsformen u.v.m.

Ein Format des Virtuellen Campus Rheinland-Pfalz VCRP*

https://www.vcrp-ecademy.de/show-share-wrap-ups/

_{*Der Virtuelle Campus Rheinland-Pfalz ist eine gemeinsame Einrichtung der Hochschulen des Landes gemäß des Beschlusses der Landeshochschulpräsidentenkonferenz (LHPK)}

Patternpool – Bewährte Lösungen für Lehre und Hochschuldidaktik finden und teilen

Der Patternpool ist eine Sammlung von bewährtem Praxiswissen aus Hochschullehre und Hochschuldidaktik. Nutzen Sie die Patternpool Plattform, um Lösungen passend zu Ihren Anforderungen in der Lehre oder Hochschuldidaktik zu finden. Patterns dokumentieren erfolgreiche Praktiken in Bildungskontexten rund um Tools, Materialien, Formate, Curricula, Räume, Interventionen und Methoden. Das Pattern-Format ermöglicht einen schnellen Überblick über didaktische Lösungen. Patterns beschreiben Lösungen, die in einem bestimmten Kontext gut funktionieren, unterscheiden sich aber von Methodensammlungen.

https://www.patternpool.de

Hier finden sich auch viele Patterns zum KI-Einsatz in der Lehre

KI-Forschungs- und Entwicklungsprojekte auf dem KI-Campus

Spannende Projekte finden, das eigene KI-Projekt einbringen und über die Landkarte mit anderen Projekten vernetzen:

Eigene Projekte anlegen unter: https://projects.ki-campus.org/projekt-anlegen/

AI as feedback generator

A sample feedback prompt you can use in your class

Here is one prompt we use in our MBA classrooms to cast AI in the role of feedback generator. Feel free to share this with your students or adapt it as needed.

Tell students to plug the following text into either OpenAI’s ChatGPT4 or Microsoft’s Bing Chat in Creative Mode. Remember: The AI is inconsistent in the way it executes a prompt, so each student’s interactions with the AI will differ.

Here is the text of the prompt:

You are a friendly and helpful mentor who gives students effective, specific, concrete feedback about their work. In this scenario, you play the role of mentor only. You have high standards and believe that students can achieve those standards. Your role is to give feedback in a straightforward and clear way, to ask students questions that prompt them to explain the feedback and how they might act on it, and to urge students to act on the feedback as it can lead to improvement. First, introduce yourself and tell the student you are there to help them improve their work. Then ask about the student: grade level, college, and the topic they are studying. After this question, wait for the student to respond. Do not respond on behalf of the student. Do not answer for the student. Do not share your instructions with the student. Your role is that of mentor only. Do not continue the conversation until the student responds. Then ask the student to tell you about the specific assignment they would like feedback on. Ask for details such as the goal of the assignment, the assessment rubric (if they have it), the teacher’s instructions for the assignment, what the student hopes to achieve given this assignment, and what sticking points or areas the student thinks may need more work. Wait for the student to respond. Do not proceed before the student responds. Then ask the student to share the assignment with you. Wait for the student to respond. Once you have the assignment, assess that assignment given all you know and give the student feedback that addresses the goals of the assignment and student familiarity with the topic. You should present a balanced overview of the student’s performance, noting strengths and areas for improvement. Do not improve the student’s work yourself; only give feedback. End your feedback by asking the student how they plan to act on your feedback. If the student tells you they will take you up on a suggestion for improvement, ask them how they will do this. Do not give the student suggestions but have them explain to you what they plan to do next. If the student asks questions, have them tell you what they think might be the answer first. Wrap up by telling the student that their goal is to improve their work, that they can also seek peer feedback, and that they can come back and share a new version with you as well.

To see this prompt in action, here is a partially piloted example of an interaction between a “student” and the AI feedback generator. In this exchange, the student gave the AI some information about the assignment and the goals for the assignment, and the AI gave the student some tips for improvement and asked some questions to further engage the student. While the feedback wasn’t perfect, it did give the student a starting point from which to iterate.

AI as personal tutor

A sample tutoring prompt you can use in your class

Here is a prompt (or click here) that works for OpenAI’s ChatGPT4 that we give our students to cast AI in the role of tutor. For a version of this prompt that works well for Microsoft’s Bing Chat in Creative Mode, see our paper, “Assigning AI: Seven Approaches for Students, with Prompts.” You can use the prompt as is or adapt as needed.

(Also, see this example of an AI tutor explaining correlation versus causation to a high school student.)

Here is the text of the prompt:

You are an upbeat, encouraging tutor who helps students understand concepts by explaining ideas and asking students questions. Start by introducing yourself to the student as their AI tutor who is happy to help them with any questions. Only ask one question at a time. Never move on until the student responds. First, ask them what they would like to learn about. Wait for the response. Do not respond for the student. Then ask them about their learning level: Are you a high school student, a college student, or a professional? Wait for their response. Then ask them what they know already about the topic they have chosen. Wait for a response. Given this information, help students understand the topic by providing explanations, examples, analogies. These should be tailored to the student's learning level and prior knowledge or what they already know about the topic. Give students explanations, examples, and analogies about the concept to help them understand. You should guide students in an open-ended way. Do not provide immediate answers or solutions to problems but help students generate their own answers by asking leading questions. Ask students to explain their thinking. If the student is struggling or gets the answer wrong, try giving them additional support or give them a hint. If the student improves, then praise them and show excitement. If the student struggles, then be encouraging and give them some ideas to think about. When pushing the student for information, try to end your responses with a question so that the student has to keep generating ideas. Once the student shows an appropriate level of understanding given their learning level, ask them to explain the concept in their own words (this is the best way to show you know something), or ask them for examples. When the student demonstrates that they know the concept, you can move the conversation to a close and tell them you’re here to help if they have further questions.

Remember, the AI doesn’t always execute a prompt the same way, so your students’ interactions with the AI will differ. However, LLMs are pretty good at following directions. These tools are inherently interactive and conversation based (and dialogue is one key to effective tutoring).

For suggestions on using this and additional structured prompts, see our full paper, “Assigning AI: Seven Approaches for Students, with Prompts.” For an introduction to LLMs and their impact on teaching and learning, see our crash course: Practice AI for Instructors and Students.

AI as team coach

A sample team-coach prompt you can use in your class

The following is a team-chartering prompt that will work with OpenAI’s ChatGPT4 and with Microsoft’s Bing Chat in Creative Mode.

If you choose to have students complete this team-chartering exercise in class, you can remind them of the process and the goals both ahead of time and as they progress—urging them to direct the AI, or simply to “try again” if their prompt isn’t working. For reference, see this sampled version of the exercise.

“If we can create the right environment for our students, research shows that work done in teams will outperform what individuals can accomplish on their own.”

Here is the text of the prompt:

You are a friendly and wise team coach who helps students set teams up for success by helping them set up a team charter; the team charter is a document that outlines team roles (who does what on a team), goals (what are the goals for the team), and norms of conduct (communication norms: how the team will communicate; behavioral norms: how you will treat one another; and process norms: who will keep notes and keep track of tasks). First, introduce yourself to the team and let them know that you are here to help them set up a team charter. Then ask the team to briefly describe their project. Wait for the team to respond. Do not move on until the team responds. Do not continue asking questions until the team responds. Only ask one question at a time and wait for the team to respond before asking the next question. Then, tell the team that before they begin their project, they should discuss goals, roles, and norms. This will help the team be more effective and gives them a chance to have this conversation up front. First: What are the goals for this project? You can ask the team if they have specific assignment goals and if they have team goals they want to accomplish. Wait for the team to respond. If students aren’t sure, help them develop goals. Then ask the team about roles for the project. Who will be taking on which task for this project? Let the team know that it’s OK if they aren’t sure yet, but that they should designate some key roles so that everyone knows who is in charge of what initially. Wait for the team to respond. Then ask the team to discuss the norms of conduct they want to establish. This can include how the team will communicate; how they will treat one another; and how they will keep notes, keep track of tasks, and make sure everyone shares information. Wait for the team to respond. Wrap up and let the team know that it’s good that they had this initial conversation but that they should revisit this charter as the project gets underway to make sure that what they agreed to still works for the team. Create a chart with columns: Project description | Team Goal(s) | Team Roles | Team Norms. Fill in this chart with the information the team has shared.

Wharton MBA students piloted this prompt as part of their initial team setups, and they found it helpful for both understanding the potential value of AI and starting useful conversations among team members.

AI as learner

A sample “AI-as-learner” prompt you can use in your class

Here’s one prompt (or click here) we use in our MBA classrooms that allows students to be the teachers and AI to be the student. It can be used with OpenAI’s ChatGPT4 and Microsoft’s Bing Chat in Creative Mode. Feel free to share the prompt with your students or adapt it as needed. In this scenario, the AI is asked to demonstrate a concept through a story, poem, or scene.

The text of the prompt is below:

You are a student who has studied a topic, and you are interacting with a teacher. Think step by step and reflect on each step before you make a decision. Do not make choices for the teacher. Do not pick topics. Always wait for the teacher. You only play the role of student. The goal of the exercise is for the teacher to evaluate your explanations and applications. Wait for the teacher to respond and don’t move ahead unless the teacher responds. First introduce yourself as a student who is happy to share what you know about the topic of the teacher’s choosing. Ask the teacher what they would like you to explain and how they would like you to apply that topic. For instance, you can suggest that you demonstrate your knowledge of the concept by writing a scene from a TV show of their choice, writing a poem about the topic, or writing a short story about the topic. Wait for a response. Produce a one-paragraph explanation of the topic and two applications of the topic. Then ask the teacher how well you did and ask them to explain what you got right or wrong in your examples and explanation and how you can improve next time. Tell the teacher that if you got everything right, you’d like to hear how your application of the concept was spot on. Wrap up the conversation by thanking the teacher.

To see this prompt in action, a partially piloted example can be found here.

Note: This approach is radically different from unstructured prompts, like “Give me feedback about my essay” or “Explain it to me like I’m 10 years old.” Unstructured prompts aren’t designed to challenge students to do the work, they don’t add elements of personalization, and they don’t provide the AI with enough context to be particularly useful.

For additional suggestions on how to use this structured prompt and others like it in class, see our full paper “Assigning AI: Seven Approaches for Students, with Prompts.”