Prompt for both the content problem space and the rhetorical problem space to support knowledge transforming with AI¶

Strategy · All strategies
Evidence · 2 claims (2 mixed) · 3 studies (2 theoretical, 1 qualitative), q1–q2 · 0 of 3 report an effect size · 1 claim rests on one study

Description¶

Building on knowledge telling vs. knowledge transforming, the article recommends that users who want to support joint knowledge transforming make use of translations between a content problem space and a rhetorical problem space, providing prompts for each. Example rhetorical prompts establish a genre and audience, while content prompts elicit alternative theories and counterarguments. This turns writing with AI from simply recording what one knows into converting knowledge into complex relational argumentation structures.

Design Implications¶

Context¶

Requirements¶

• Users must possess rhetorical knowledge about genres and be able to phrase separate prompts addressing content and rhetorical issues

Constraints¶

• Conceptual and empirical research on prompting processes in human-AI communication is described as urgently needed; optimal prompts are not yet established

Target Learners¶

• users of generative AI tools for writing and learning
• novice and expert writers

Target Learning Goals¶

• knowledge transformation
• argumentation skills
• text writing

Claims¶

• Hybridization of authorship blends human and AI-generated content, often without learners' explicit awareness of the boundary, normalizing formulaic rhetorical structures [~W]
• Generative AI tools do not possess conceptual knowledge or conscious understanding, relying only on word patterns and probabilities [~W]

Related Strategies¶

Examples¶

-

Key Sources¶

• Ulrike Cress · Joachim Kimmerle. (2023). Co-constructing knowledge with generative AI tools: Reflections from a CSCL perspective. Intern. J. Comput.-Support. Collab. Learn. https://doi.org/10.1007/s11412-023-09409-w