arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.11441cs.LGcs.CL
收藏

社会学习:迈向大型语言模型的协作学习

Social Learning: Towards Collaborative Learning with Large Language Models

EPFL(洛桑联邦理工学院);Google(谷歌公司)

Amirkeivan Mohtashami, Florian Hartmann, Sian Gooding, Lukas Zilka, Matt Sharifi, Blaise Aguera y Arcas

AI总结:

本文提出社会学习框架,使大语言模型通过自然语言以隐私感知方式共享知识,并评估了抽象提示与合成示例两种迁移方法,性能与原始标签相当且记忆化低。

摘要:

我们在大语言模型(LLMs)的背景下引入了“社会学习”框架,其中模型以隐私感知的方式使用自然语言相互共享知识。我们提出并评估了两种在LLMs之间进行知识迁移的方法。在第一种场景中,我们允许模型生成旨在教授任务的抽象提示。在我们的第二种方法中,模型通过生成合成示例来迁移知识。我们在多样化的数据集上评估这些方法,并将记忆化量化为隐私损失的代理指标。这些受社会学习启发的技术产生了有前景的结果,且对原始数据的记忆化程度较低。特别是,我们表明使用这些方法的性能与使用原始标签和提示的结果相当。我们的工作证明了社会学习对LLMs的可行性,建立了基线方法,并突出了未来工作的几个未探索领域。

英文摘要:

We introduce the framework of "social learning" in the context of large language models (LLMs), whereby models share knowledge with each other in a privacy-aware manner using natural language. We present and evaluate two approaches for knowledge transfer between LLMs. In the first scenario, we allow the model to generate abstract prompts aiming to teach the task. In our second approach, models transfer knowledge by generating synthetic examples. We evaluate these methods across diverse datasets and quantify memorization as a proxy for privacy loss. These techniques inspired by social learning yield promising results with low memorization of the original data. In particular, we show that performance using these methods is comparable to results with the use of original labels and prompts. Our work demonstrates the viability of social learning for LLMs, establishes baseline approaches and highlights several unexplored areas for future work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑