Personalized responses remain semantically grounded in the shared knowledge base while varying in surface-level expression and structure¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Pairwise cosine similarity and ROUGE comparisons of 97 responses to a representative question showed high semantic similarity but substantially lower lexical similarity. → Saptarshi Basu 2026

Evidence¶

Saptarshi Basu 2026¶

Saptarshi Basu, Sandeep Kakar, Ashok Goel. (2026). A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant. https://arxiv.org/abs/2609.03402 doi:10.48550/arxiv.2609.03402

q2 · i? · design · r2

Numerical result shown in Figure 1: all-MiniLM-L6-v2 embeddings with pairwise cosine similarity and ROUGE scores computed for the 97 responses to one representative question. Qualitative snippets also illustrated strategy differences between beginner and advanced profiles.

"Fig- ure 1 shows high semantic similarity but substantially lower lexical similarity, indicating that responses remain semanti- callygroundedwhilevaryinginsurface-levelexpressionand structure."

Discussion¶

Related Claims¶

• Prompt-based personalization of an LLM/RAG teaching assistant produces measurable variation in response expression, length, and complexity across personalization conditions — a broader claim this one bears on
• Cluster membership showed a strong multivariate effect on standard text-similarity metrics (Pillai's trace = 0.85, F(12, 248) = 15.31, p < 0.001) — related