PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning

arXiv:2609.18861 · cs.CL · Submitted 2026-09-16 · Read on arXiv

cs.CL

Submitted: 2026-09-16

Updated: 2026-09-16

Comments: Accepted to AACL-IJCNLP 2026 Main Conference

Code: https://github.com/BUAA-IRIP-LLM/PersonaPath

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptivity — 42× in this paper · explained in 1 episode
• Benchmark — 38× in this paper · explained in 2 episodes
• Archetype — 26× in this paper · explained in 1 episode
• Knowledge Graph — 17× in this paper · explained in 7 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Core — 10× in this paper · explained in 2 episodes
• Knowledge Tracing — 9× in this paper
• Alignment — 8× in this paper · explained in 1 episode
• RAG — 8× in this paper · explained in 3 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Hallucination — 7× in this paper · explained in 3 episodes
• Adaptability — 5× in this paper · explained in 1 episode
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Knowledge graphs — 4× in this paper · explained in 2 episodes
• Personalization — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Breadth of Educational Disciplines — 3× in this paper
• Chain-of-Thought (CoT) — 3× in this paper · explained in 4 episodes
• Rich Semantics — 3× in this paper
• Textbook-level Prerequisite Graph — 3× in this paper
• Zone of Proximal Development — 3× in this paper
• Chain-of-Thought (CoT) Prompting — 2× in this paper · explained in 3 episodes
• Coefficient of Variation — 2× in this paper
• Deep Knowledge Tracing — 2× in this paper
• Evaluation Dimensions — 2× in this paper · explained in 3 episodes
• Graph Construction — 2× in this paper · explained in 3 episodes
• Hierarchical Knowledge Structure — 2× in this paper
• Personally Identifiable Information — 2× in this paper
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Axioms — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Directed Acyclic Graph — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Illustration of Exercise-Centric — 1× in this paper
• International Conference on Educational Data Mining — 1× in this paper
• International Conference on World Wide Web — 1× in this paper
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Metacognition — 1× in this paper · explained in 5 episodes
• Most Learning Path Recommendation — 1× in this paper
• Provenance — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Zero-shot and Chain-of-Thought — 1× in this paper

Sources

• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition
• Are Large Language Models Effective Knowledge Graph Constructors?
• Constructing a personalized learning path using genetic algorithms approach
• The Llama 3 Herd of Models
• Inverse Scaling: When Bigger Isn't Better
• Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning
• Bringing Generative AI to Adaptive Learning in Education
• Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis
• Large Language Models for Generative Information Extraction: A Survey
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering