Name the target theory in the prompt without supplying full reference papers when practical, usable codebooks are the goal¶

Strategy · All strategies
Evidence · no claims cited

Description¶

When prompting an LLM for theory-informed codebook development, specify the theoretical framework by name rather than pasting full papers or long reference lists. The study's comparison found that "naming the theory without including full references produced the most practical and usable codebook", while full-text supply enhanced alignment but reduced applicability, so "attention to prompt design is required". Use this strategy when the framework is well established in the model's training data and the priority is codes that can actually be applied to the dataset.

Design Implications¶

Context¶

Requirements¶

• A theoretical framework well established enough to be represented in the LLM's training data
• Human evaluation of the resulting codebook's practicality and theoretical alignment

Constraints¶

• Supplying full papers may still be preferable when maximizing theoretical alignment matters more than applicability

Target Learners¶

• education researchers using LLMs for qualitative coding

Target Learning Goals¶

• efficient theory-grounded codebook development for qualitative and mixed-methods learning research

Related Strategies¶

Examples¶

-

Key Sources¶

• Zambrano, A.F., Wei, Z., Zhang, J., Baker, R.S., Ocumpaugh, J., Barany, A., Liu, X., Ginger, J., Paquette, L., Zhou, Y., & Borchers, C. (2026). Data Plus Theory Equals Codebook: Leveraging LLMs for Human-AI Codebook Development. Journal of Educational Data Mining, Volume 18, No 1. https://osf.io/g3z4x. doi:10.35542/osf.io/4wyqc_v1