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 2402.01867cs.LGcs.CL
收藏

利用大型语言模型进行提示弱监督中的结构学习

Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision

Cornell University(康奈尔大学);Brown University(布朗大学);University of Washington(华盛顿大学)

Jinyan Su, Peilin Yu, Jieyu Zhang, Stephen H. Bach

AI总结:

本研究提出结构精炼模块,利用LLM提示相似性学习弱监督中标注函数的依赖结构,通过LaRe和CosGen提升PromptedWS流程性能,在基准任务上最高提升12.7个百分点。

摘要:

提示弱监督(PromptedWS)将预训练的大型语言模型(LLMs)作为弱监督框架中标注函数(LFs)的基础,以获取大规模标注数据集。我们进一步扩展了LLMs在循环中的使用,以解决弱监督中的关键挑战之一:学习监督源之间的统计依赖结构。在这项工作中,我们询问LLM这些提示的LFs有多相似。我们提出了一种结构精炼模块(Structure Refining Module),这是一种简单而有效的初步方法,基于提示的相似性,利用嵌入空间中的内在结构。结构精炼模块的核心是标注函数移除(LaRe)和相关性结构生成(CosGen)。与以往从弱标签中学习依赖关系的方法相比,我们的方法发现了LFs固有的依赖关系,并且较少依赖于数据。我们展示了我们的结构精炼模块在基准任务上将PromptedWS流程提升了高达12.7个百分点。我们还通过全面的消融实验和分析探索了效率与性能之间的权衡。该项目的代码可在https://github.com/BatsResearch/su-bigdata23-code找到。

英文摘要:

Prompted weak supervision (PromptedWS) applies pre-trained large language models (LLMs) as the basis for labeling functions (LFs) in a weak supervision framework to obtain large labeled datasets. We further extend the use of LLMs in the loop to address one of the key challenges in weak supervision: learning the statistical dependency structure among supervision sources. In this work, we ask the LLM how similar are these prompted LFs. We propose a Structure Refining Module, a simple yet effective first approach based on the similarities of the prompts by taking advantage of the intrinsic structure in the embedding space. At the core of Structure Refining Module are Labeling Function Removal (LaRe) and Correlation Structure Generation (CosGen). Compared to previous methods that learn the dependencies from weak labels, our method finds the dependencies which are intrinsic to the LFs and less dependent on the data. We show that our Structure Refining Module improves the PromptedWS pipeline by up to 12.7 points on the benchmark tasks. We also explore the trade-offs between efficiency and performance with comprehensive ablation experiments and analysis. Code for this project can be found in https://github.com/BatsResearch/su-bigdata23-code.

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。

↑