Abstract
Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors derived from the transformer. However, the working mechanisms and optimization of these vectors are yet to be thoroughly explored. In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector. Inspired by the works on model soup and momentum-based gradient descent, we propose inner and momentum optimization methods that are applied to refine the state vector progressively as test-time adaptation. Moreover, we simulate state vector aggregation in the multiple example setting, where demonstrations comprising numerous examples are usually too lengthy for regular ICL, and further propose a divide-and-conquer aggregation method to address this challenge. We conduct extensive experiments using Llama-2 and GPT-J in both zero-shot setting and few-shot setting. The experimental results show that our optimization method effectively enhances the state vector and achieves the state-of-the-art performance on diverse tasks. Code is available at this https URL
Abstract (translated)
大语言模型（LLMs）表现出从仅几个示例中进行In-Context学习（ICL）的令人印象深刻的能力。最近的工作表明，通过从Transformer中提取压缩向量获得的函数可以表示为LLMs训练得到的参数。然而，这些向量的运行机制和优化尚未被深入研究。在本文中，我们通过全面分析这些压缩向量，将参数训练与梯度下降中的参数进行类比，并引入了状态向量概念，来填补这一空白。受到模型 soup 和基于动量梯度的优化工作的启发，我们提出了内化和动量优化方法，应用于在测试时间适应过程中逐步优化状态向量。此外，我们还通过多个示例设置下的状态向量聚合方法，解决了这种挑战。我们在零 shot和少样本设置中使用Llama-2和GPT-J进行广泛的实验。实验结果表明，我们的优化方法有效地增强了状态向量，并在各种任务上实现了最先进的性能。代码可以从该链接获取：https://llama2.github.io/experiments/icl_results.html
URL
https://arxiv.org/abs/2404.11225
