From Prediction to Precision: Leveraging LLMs for Equitable and Data-Driven Writing Placement in Developmental Education

🤖 Plain-English Summary

Accurate text classification and placement remain challenges in U.S. Gemini and Claude also demonstrated strong correlation with human ratings, with Claude achieving the highest Pearson scores (ρ = 0.75; 1-step, ρ = 0.73; 2-step) vs.

🔑 Key Findings

• higher education, with traditional automated systems like Accuplacer functioning as "black-box" models with limited assessment transparency.
• This study evaluates Large Language Models (LLMs) as complementary placement tools by comparing their classification performance against a human-rated gold standard and Accuplacer.
• A 450-essay corpus was classified using Claude, Gemini, GPT-3.5-turbo, and GPT-4o across four prompting strategies: Zero-shot, Few-shot, Enhanced, and Enhanced+ (definitions with examples).

🔗 Related Resources