Let students choose the complexity level of the LLM feedback¶

Strategy · All strategies
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

In LEAP, students can select the complexity of the feedback they receive for each submitted response: low (very easy-to-understand feedback in five sentences for a secondary school student), middle (feedback for a high school student, the default), or high (very elaborate feedback using physical formulas in MathJax format). The article states students "can choose the complexity level of the feedback ... for each submitted response, based on their individual preferences."

Design Implications¶

Context¶

Requirements¶

• Complexity instructions are embedded in the system message set by the platform, so teachers need not write them separately

Constraints¶

Target Learners¶

• secondary and high school physics students

Target Learning Goals¶

• self-regulated learning through adaptive feedback difficulty

Claims¶

• Systematic prompting of an LLM can generate cognitively activating formative feedback aligned with research-based scaffold types (demonstrated, not yet empirically validated) [+W]

Related Strategies¶

• Leap Llm Formative Feedback Platform
• Academic Choice (Planning, Working, Reflecting)
• Learning Menus
• Tiered Assignments

Examples¶

-

Key Sources¶

• Steinert, S., Avila, K. E., Ruzika, S., Kuhn, J., & Küchemann, S. (2024). Harnessing large language models to develop research-based learning assistants for formative feedback. Smart Learning Environments. https://doi.org/10.1186/s40561-024-00354-1