Removing explicit mastery information from learner profiles mainly degrades Adaptivity¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-17 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Omitting the Mastery field reduces Adaptivity by 26.1 percentage points for Qwen3-30B-A3B (CoT) while Validity changes much less. → Yu Liu 2026

Evidence¶

Yu Liu 2026¶

Yu Liu, Zeming Liu, Tianle Zhang, Zihao Cheng, Yuhang Guo, Kehai Chen, Min Zhang, Yunhong Wang, Haifeng Wang. (2026). PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning. arXiv. https://arxiv.org/abs/2609.18861 doi:10.48550/arxiv.2609.18861

q2 · i? · design · r2

Ablation on Basic Education personas (Table 6) in which the Mastery field is removed while goal and curriculum context are held fixed, turning the input into a coarse learner description. The article reports the printed percentage-point drops in Adaptivity across models; no effect size is printed.

"Removing mastery information reduces Adaptivity by 26.1 percentage points for Qwen3-30B-A3B (CoT), while Validity changes much less."

Discussion¶

Related Claims¶

• Contextual noise from irrelevant textbooks broadly degrades KC planning, most in Validity and Efficiency — related
• Chain-of-Thought prompting improves KC planning for Qwen models but its effect varies by model and educational stage — related
• Adaptivity to individual learners is the primary bottleneck for LLMs in KC path planning — a broader claim this one bears on
• Static Knowledge Grounding and Dynamic Personal Memory are complementary: removing both yields the largest quality degradation — related
• One-shot path generation raises Validity but lowers Adaptivity and Efficiency relative to step-by-step interaction — related