SOTAVerified

Knowledge Tracing

Knowledge Tracing is the task of modelling student knowledge over time so that we can accurately predict how students will perform on future interactions. Improvement on this task means that resources can be suggested to students based on their individual needs, and content which is predicted to be too easy or too hard can be skipped or delayed.

Source: Deep Knowledge Tracing

Papers

Showing 125 of 215 papers

TitleStatusHype
Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding TutorsCode2
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing ModelsCode2
Improving Knowledge Tracing via Pre-training Question EmbeddingsCode1
Enhancing Knowledge Tracing with Concept Map and Response DisentanglementCode1
GIKT: A Graph-based Interaction Model for Knowledge TracingCode1
HD-KT: Advancing Robust Knowledge Tracing via Anomalous Learning Interaction DetectionCode1
Deep Knowledge TracingCode1
Context-Aware Attentive Knowledge TracingCode1
DyGKT: Dynamic Graph Learning for Knowledge TracingCode1
Enhancing Knowledge Tracing via Adversarial TrainingCode1
Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMsCode1
Forgetting-aware Linear Bias for Attentive Knowledge TracingCode1
Adaptive and Personalized Exercise Generation for Online Language LearningCode1
GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative FilteringCode1
A Survey of Knowledge Tracing: Models, Variants, and ApplicationsCode1
Contrastive Learning for Knowledge TracingCode1
Application of Deep Self-Attention in Knowledge TracingCode1
Convolutional Knowledge Tracing: Modeling Individualization in Student Learning ProcessCode1
Disentangled Knowledge Tracing for Alleviating Cognitive BiasCode1
Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge TracingCode1
Dynamic Student Classiffication on Memory Networks for Knowledge TracingCode1
Assessing Student's Dynamic Knowledge State by Exploring the Question Difficulty EffectCode1
Assessing the Performance of Online Students -- New Data, New Approaches, Improved AccuracyCode1
Code-DKT: A Code-based Knowledge Tracing Model for Programming TasksCode1
DGEKT: A Dual Graph Ensemble Learning Method for Knowledge TracingCode1
Show:102550
← PrevPage 1 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SAKTAcc70.73Unverified
2SAINT+AUC0.79Unverified
3SAINTAUC0.78Unverified
4PEBG+DKTAUC0.78Unverified
5PEBG+DKVMNAUC0.78Unverified
6DKVMNAUC0.77Unverified
7DKTAUC0.76Unverified
8GIKTAUC0.75Unverified
#ModelMetricClaimedVerifiedStatus
1DKTAUC0.86Unverified
2BKTAUC0.67Unverified