Hybrid micro-level personalization framework combining learner-driven preferences with system-driven Bloom's Taxonomy cognitive assessment

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

A framework for personalizing LLM/RAG teaching assistants at the level of individual student questions. It represents learner characteristics through self-assessed metacognitive knowledge and question-level cognitive complexity via Bloom's Taxonomy, plus five Felder-Silverman-derived preferences (abstraction, verbosity, perception, processing, understanding). The article states "The combination of learner characteristics and preferences produces 96 distinct learner profiles" and that "This creates a hybrid framework combining learner-driven adaptability with system-driven adaptivity." It contrasts with prior adaptive systems that adapt content selection or sequencing by instead adapting response form.

Design Implications

Context

Requirements

• Learner preferences are explicitly selected by students while cognitive demand is inferred by the system via a fine-tuned BERT-based Bloom classifier (0.92 test accuracy)
• An engineered prompt encoding all learner attributes must condition the LLM within the existing RAG pipeline and course-specific knowledge base

Constraints

• Personalization modifies the form and presentation of responses while preserving grounding in retrieved instructional content
• Treated as user-selected preferences rather than fixed psychometric classifications

Target Learners

• online and course-based higher-education students (e.g., KBAI graduate course)

Learning Goals

• tailoring instructional explanations to learner preferences and question cognitive complexity

Claims

• Prompt Personalization Measurable Response Variation [+M]
• Abstraction Processing Significant Self Assessment Not [+M]

Related Designs

• Bloom-level mapping of exercise difficulty levels in AI exercise generation
• ProPACT Hybrid-AI feedback system with five feedback tools and hierarchical trigger policy

Examples

-

Key Sources

• 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

Page metadata

Field	Value
type	design
id	hybrid-micro-personalization-framework
title	Hybrid micro-level personalization framework combining learner-driven preferences with system-driven Bloom's Taxonomy cognitive assessment
description	A framework for personalizing LLM/RAG teaching assistants at the level of individual student questions.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — saptarshi-basu-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.