相关论文: Model Balancing Helps Low-data Training and Fine-t…

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions,…

Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further…

With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained…

Federated Learning (FL) trains a machine learning model on distributed clients without exposing individual data. Unlike centralized training that is usually based on carefully-organized data, FL deals with on-device data that are often…

The quality of datasets is one of the key factors that affect the accuracy of aerodynamic data models. For example, in the uniformly sampled Burgers' dataset, the insufficient high-speed data is overwhelmed by massive low-speed data.…

Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…

Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of LLM pre-training. We show that data mixtures that perform well at smaller…

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the…

Recent advances in natural language processing have leveraged instruction tuning to enhance Large Language Models (LLMs) for table-related tasks. However, previous works train different base models with different training data, lacking an…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data. Motivated by the effectiveness and robustness of…

In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient…

Instruction tuning has unlocked powerful capabilities in large language models (LLMs), effectively using combined datasets to develop generalpurpose chatbots. However, real-world applications often require a specialized suite of skills…

Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment…

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But…