Related papers: Cuff-KT: Tackling Learners' Real-time Learning Pat…

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Existing approaches to mathematical reasoning with large language models (LLMs) rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation. While efforts have been made to combine these…

Test-time training (TTT) enhances model performance by explicitly updating designated parameters prior to each prediction to adapt to the test data. While TTT has demonstrated considerable empirical success, its theoretical underpinnings…

The scaling of model and data sizes has reshaped the AI landscape, establishing finetuning pretrained models as the standard paradigm for solving downstream tasks. However, dominant finetuning methods typically rely on weight adaptation,…

E-learning environments are increasingly harnessing large language models (LLMs) like GPT-3.5 and GPT-4 for tailored educational support. This study introduces an approach that integrates dynamic knowledge graphs with LLMs to offer nuanced…

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Fine-tuning large language models is becoming ever more impractical due to their rapidly-growing scale. This motivates the use of parameter-efficient adaptation methods such as prompt tuning (PT), which adds a small number of tunable…

Knowledge Tracing (KT) is to trace the knowledge of students as they solve a sequence of problems represented by their related skills. This involves abstract concepts of students' states of knowledge and the interactions between those…

Deep neural networks demonstrate strong performance under aligned training-test distributions. However, real-world test data often exhibit domain shifts. Test-Time Adaptation (TTA) addresses this challenge by adapting the model to test data…

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with only unlabeled test data streams. Most of the previous TTA methods have achieved great success on simple test data streams such as independently…

Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy, most models rely on deterministic vector embeddings and…

Knowledge tracing (KT) is a crucial technique to predict students' future performance by observing their historical learning processes. Due to the powerful representation ability of deep neural networks, remarkable progress has been made by…

Knowledge components (KCs) mapped to problems help model student learning, tracking their mastery levels on fine-grained skills thereby facilitating personalized learning and feedback in online learning platforms. However, crafting and…

Knowledge tracing (KT) which aims at predicting learner's knowledge mastery plays an important role in the computer-aided educational system. In recent years, many deep learning models have been applied to tackle the KT task, which have…

Large Language Models (LLMs) face the "knowledge cutoff" challenge, where their frozen parametric memory prevents direct internalization of new information. While Supervised Fine-Tuning (SFT) is commonly used to update model knowledge, it…

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…

Capturing the evolving trends of user interest is important for both recommendation systems and advertising systems, and user behavior sequences have been successfully used in Click-Through-Rate(CTR) prediction problems. However, if the…

The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement…