Related papers: REInstruct: Building Instruction Data from Unlabel…
Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…
Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While high-quality data is paramount, it is often scarce; conversely, abundant low-quality data is…
Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…
Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations in terms of both data and algorithm. For training data,…
Small language models (SLMs) enable low-cost, private, on-device inference, but they often fail on problems that require specialized domain knowledge or multi-step reasoning. Existing approaches for improving reasoning either rely on scale…
A novel approach to the fully automated, unsupervised extraction of dependency grammars and associated syntax-to-semantic-relationship mappings from large text corpora is described. The suggested approach builds on the authors' prior work…
Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been…
One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in a task-agnostic way,…
Datasets nowadays are generally constructed from multiple sources and using different synthetic techniques, making data de-noising and de-duplication crucial before being used for post-training. In this work, we propose to perform…
This paper explores zero-label learning in Natural Language Processing (NLP), whereby no human-annotated data is used anywhere during training and models are trained purely on synthetic data. At the core of our framework is a novel approach…
Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…
The adaptation of Large-Scale Language Models (LLMs) to specific domains depends on high-quality fine-tuning datasets, particularly in instructional format (e.g., Question-Answer - Q&A). However, generating these datasets, particularly from…
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…
Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…
Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…
In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…
Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the…
The effectiveness of large language models (LLMs) in conversational AI is hindered by their reliance on single-turn supervised fine-tuning (SFT) data, which limits contextual coherence in multi-turn dialogues. Existing methods for…
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation. However,…
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of…