Related papers: Intrinsic Dimensionality Explains the Effectivenes…

Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based optimization. We propose HyperTuning, a novel approach to…

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Parameter-efficient fine-tuning aims to achieve performance comparable to fine-tuning, using fewer trainable parameters. Several strategies (e.g., Adapters, prefix tuning, BitFit, and LoRA) have been proposed. However, their designs are…

Pre-trained Transformers are now ubiquitous in natural language processing, but despite their high end-task performance, little is known empirically about whether they are calibrated. Specifically, do these models' posterior probabilities…

High-dimensional predictive models, those with more measurements than observations, require regularization to be well defined, perform well empirically, and possess theoretical guarantees. The amount of regularization, often determined by…

Fine-tuning large language models (LLMs) can cause them to lose their general capabilities. However, the intrinsic mechanisms behind such forgetting remain unexplored. In this paper, we begin by examining this phenomenon by focusing on…

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters using light-weight adaptation has shown considerable success…

Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Recent breakthroughs and successful deployment of large language and vision models in a constrained environment predominantly follow a two phase approach. First, large models are trained to achieve peak performance, followed by a model…

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Several studies have investigated the reasons behind the effectiveness of fine-tuning, usually through the lens of probing. However, these studies often neglect the role of the size of the dataset on which the model is fine-tuned. In this…

Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inference efficiency of pre-trained models. Meanwhile, they…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Fine-tuning large language models (LLMs) with high parameter efficiency for downstream tasks has become a new paradigm. Low-Rank Adaptation (LoRA) significantly reduces the number of trainable parameters for fine-tuning. Although it has…