Adapt the two question-design strategies across disciplines: novel scenarios for logic puzzles, guided reasoning for proofs and critical analyses¶

Strategy · All strategies
Evidence · no claims cited

Description¶

In future work, the authors recommend extending the framework beyond computer science: "Strategy 1 is well-suited for novel thought experiments or logic puzzles, while Strategy 2 can also be applied to constructing proofs in STEM or even outlining critical analyses in the humanities." They identify the primary challenge for cross-disciplinary scaling as the creation of effective, domain-specific question sets by educators.

Design Implications¶

Context¶

Requirements¶

• Educators must create effective, domain-specific question sets for each new discipline

Constraints¶

• The primary challenge for cross-disciplinary scaling lies in creating effective, domain-specific question sets

Target Learners¶

• students across STEM and humanities disciplines

Target Learning Goals¶

• constructing proofs, outlining critical analyses, and solving novel logic puzzles through teaching an LLM

Related Strategies¶

• Logic Puzzles
• Adapt the guided inquiry policy co-design activity across disciplines, framing AI as a sociotechnical system
• Design questions with engineered knowledge gaps LLMs cannot bridge alone, via non-existing scenarios and guided mathematical reasoning

Examples¶

-

Key Sources¶

• Xinming Yang, Haasil Pujara, Jun Li. (2025). Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education. Published as a conference paper at COLM 2025. https://arxiv.org/abs/2508.05979