相关论文: MSign: An Optimizer Preventing Training Instabilit…

Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficient at extreme scale. Although Adam remains the dominant optimizer for large-scale…

Machine learning is a powerful tool for building predictive models. However, it is vulnerable to adversarial attacks. Fast Gradient Sign Method (FGSM) attacks are a common type of adversarial attack that adds small perturbations to input…

Restricted Boltzmann machines (RBMs) are a powerful class of generative models, but their training requires computing a gradient that, unlike supervised backpropagation on typical loss functions, is notoriously difficult even to…

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Continual pre-training has increasingly become the predominant approach for adapting Large Language Models (LLMs) to new domains. This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in…

We train, for the first time, large language models using FP8 precision on datasets up to 2 trillion tokens -- a 20-fold increase over previous limits. Through these extended training runs, we uncover critical instabilities in FP8 training…

Emergence, the phenomenon of a rapid performance increase once the model scale reaches a threshold, has achieved widespread attention recently. The literature has observed that monosemantic neurons in neural networks gradually diminish as…

Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Current safety alignment techniques, however, harbor inherent vulnerabilities due to their reliance…

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Adam has proven remarkable successful in training deep neural networks, but the mechanisms underlying its empirical successes and limitations remain underexplored. In this study, we demonstrate that the effectiveness of Adam stems largely…

Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstrations, predictions…

While various avenues of research have been explored for iterative pruning, little is known what effect pruning has on zero-shot test performance and its potential implications on the choice of pruning criteria. This pruning setup is…

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models…

Existing machine unlearning (MU) approaches exhibit significant sensitivity to hyperparameters, requiring meticulous tuning that limits practical deployment. In this work, we first empirically demonstrate the instability and suboptimal…

Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the…

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…