baumhaus dot digital :: baumhaus.digital/Miscellanous/Presentations/AE54/NARRATIVE PRIMER: EMPOWERMENT THROUGH GENERATIVE STORYTELLING/Narrative AI in Education

A human-machine peer learning curriculum (i.e., a HMPL-C) is a planned sequence of educational instructions–i.e., a curriculum–which involves:
1. At least one human learner G, H, I, ... which gradually develops her/his/their skill Γ.
2. At least one artificial learner a, b, c, ... which gradually develops its/her/his/their skill σ.
3. Activities by means of which G (resp. H, I, etc.) develops her/his/their skill Γ, which directly involve knowledge and competence exhibited by a (resp. b, c, etc.).
4. Activities by means of which a (resp. b, c, etc.) develops her/his/their skill σ, which directly involve knowledge and competence exhibited by G (resp. H, I, etc.).

...for example, if the child’s favorite toy is a teddy bear named "Mr. Fluffy," the NP might create a story where Mr. Fluffy becomes the protagonist, embarking on an adventure to save the magical land of Ice Cream, where the child’s favorite type, such as chocolate mint, is at risk of melting. The narrative could further incorporate the child’s preferred outdoor activities—like cycling or playing soccer—where Mr. Fluffy must complete tasks that mirror these activities to solve problems within the story.

Learning Graph consists of:

Learner States (Vertices) :: Represent child's current or potential level of knowledge and skill in a specific domain.

Activities (Edges) that move the learner from one state to another, categorized as:

Listen:: The child listens to a story or explanation.

Imitate:: The child repeats phrases or mimics patterns.

Narrate:: The child retells stories or creates new ones.

Test:: The child answers questions or solves problems.

Feedback:: The NP provides corrective or reinforcing feedback.

In narrative AIED, we employ a library of narrative templates derived from classic literature, including Aesop’s fables, the Panchatantra, and Grimm's fairy tales.

These templates serve as FILL-IN-THE-SLOT FRAMEWORKS for story generation, allowing the LLM to customize narratives based on:

Pupil's Profile:: Personal interests, preferences, and learning needs.

Knowledge State:: Current mastery level in various subjects.

Learning Objectives:: Specific curricular goals targeted during the session.