Related papers: AlignKT: Explicitly Modeling Knowledge State for K…

This paper introduces ES-KT-24, a novel multimodal Knowledge Tracing (KT) dataset for intelligent tutoring systems in educational game contexts. Although KT is crucial in adaptive learning, existing datasets often lack game-based and…

Modern artificial intelligence systems depend heavily on large datasets for both training and transferring knowledge between models. Knowledge distillation, transfer learning, and dataset distillation have made such transfers more…

Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional…

Deep Knowledge Tracing (DKT) models student learning behavior by using Recurrent Neural Networks (RNNs) to predict future performance based on historical interaction data. However, the original implementation relied on standard RNNs in the…

Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Personalized learning systems have emerged as a promising approach to enhance student outcomes by tailoring educational content, pacing, and feedback to individual needs. However, most existing systems remain fragmented, specializing in…

Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a…

As a crucial step to enhance LLMs alignment with human intentions, Instruction Fine-Tuning (IFT) has a high demand on dataset quality. However, existing IFT datasets often contain knowledge that is inconsistent with LLMs' internal knowledge…

We propose a new approach, Knowledge Distillation using Optimal Transport (KNOT), to distill the natural language semantic knowledge from multiple teacher networks to a student network. KNOT aims to train a (global) student model by…

While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting…

Emerging Knowledge Tracing (KT) models, particularly deep learning and attention-based Knowledge Tracing, have shown great potential in realizing personalized learning analysis via prediction of students' future performance based on their…

Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being…

Many text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often depend on…

Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high…

Semantic networks, such as the knowledge graph, can represent the knowledge leveraging the graph structure. Although the knowledge graph shows promising values in natural language processing, it suffers from incompleteness. This paper…

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing Web-scale KGs. Over the course of its development, the label supervision has been considered…

We address the challenge of building domain-specific knowledge models for industrial use cases, where labelled data and taxonomic information is initially scarce. Our focus is on inductive link prediction models as a basis for practical…

Deep neural networks often have a huge number of parameters, which posts challenges in deployment in application scenarios with limited memory and computation capacity. Knowledge distillation is one approach to derive compact models from…

Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by…