Related papers: Token-Efficient Leverage Learning in Large Language Models

Token-Efficient Leverage Learning in Large Language Models

URL: http://arxiv.org/abs/2404.00914v1
Date: Mon, 1 Apr 2024 04:39:44 GMT
Title: Token-Efficient Leverage Learning in Large Language Models
Authors: Yuanhao Zeng, Min Wang, Yihang Wang, Yingxia Shao,
Abstract summary: Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks compound the challenge. We present a streamlined implement of this methodology called Token-Efficient Leverage Learning (TELL)
Score: 13.830828529873056
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks compound the challenge. To address the twin hurdles, we introduce \textbf{Leverage Learning}. We present a streamlined implement of this methodology called Token-Efficient Leverage Learning (TELL). TELL showcases the potential of Leverage Learning, demonstrating effectiveness across various LLMs and low-resource tasks, ranging from $10^4$ to $10^6$ tokens. It reduces task data requirements by up to nearly an order of magnitude compared to conventional Supervised Fine-Tuning (SFT) while delivering competitive performance. With the same amount of task data, TELL leads in improving task performance compared to SFT. We discuss the mechanism of Leverage Learning, suggesting it aligns with quantization hypothesis and explore its promising potential through empirical testing.

Related papers

Empirical Insights on Fine-Tuning Large Language Models for Question-Answering [50.12622877002846]
Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can be fine-tuned for the question-answering (QA) task. We categorize supervised fine-tuning (SFT) data based on the extent of knowledge memorized by the pretrained LLMs. Our experiments show that as few as 60 data points during the SFT stage can activate the knowledge encoded during pre-training, enabling LLMs to perform the QA task.
arXiv Detail & Related papers (2024-09-24T07:38:38Z)
Defining Boundaries: A Spectrum of Task Feasibility for Large Language Models [6.008311204104302]
Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the required skills surpassing their capabilities.
arXiv Detail & Related papers (2024-08-11T22:58:23Z)
SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z)
Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
arXiv Detail & Related papers (2024-06-07T11:37:45Z)
Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
arXiv Detail & Related papers (2024-03-12T13:31:14Z)
Online Cascade Learning for Efficient Inference over Streams [9.516197133796437]
Large Language Models (LLMs) have a natural role in answering complex queries about data streams. We propose online cascade learning, the first approach to address this challenge. We formulate the task of learning cascades online as an imitation-learning problem.
arXiv Detail & Related papers (2024-02-07T01:46:50Z)
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
arXiv Detail & Related papers (2023-10-10T16:38:49Z)
OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs. Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
arXiv Detail & Related papers (2023-05-24T10:08:04Z)
Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance [1.863067234952186]
We investigate model-agnostic meta-learning algorithm(MAML) in low-resource financial NLU tasks. Our models achieve the state-of-the-art performance according to the experimental results.
arXiv Detail & Related papers (2023-03-06T02:24:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.