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 2402.13414cs.LGcs.CL
收藏

利用大型语言模型作为事后修正器

Harnessing Large Language Models as Post-hoc Correctors

Aarhus University(奥胡斯大学);Microsoft(微软公司)

Zhiqiang Zhong, Kuangyu Zhou, Davide Mottin

AI总结:

本文提出免训练框架LlmCorr,利用大型语言模型作为事后修正器,通过构建情境知识数据库并借助情境学习能力,为任意ML模型预测提供修正,在文本分析和分子预测任务上性能提升高达39%。

摘要:

随着机器学习(ML)模型规模的增大以及对更高质量训练数据的需求,重新训练和微调这些模型的相关费用正在迅速攀升。受大型语言模型(LLMs)近年来在不同领域取得的瞩目成就的启发,本文深入探讨了一个问题:LLMs能否以极低的成本高效提升ML模型的性能?我们证明,通过我们提出的免训练框架LlmCorr,一个LLM可以作为事后修正器,为任意ML模型的预测提出修正建议。具体而言,我们通过整合数据集的标签信息和ML模型在验证数据集上的预测,构建了一个情境知识数据库。利用LLMs的情境学习能力,我们要求LLM总结ML模型出错的情况以及主要预测与真实标签之间的相关性。随后,LLM能够将其获得的知识迁移,为ML模型的预测提出修正建议。我们在文本分析和具有挑战性的分子预测上的实验结果表明,LlmCorr将多种模型的性能提升了高达39%。

英文摘要:

As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowledge database by incorporating the dataset's label information and the ML model's predictions on the validation dataset. Leveraging the in-context learning capability of LLMs, we ask the LLM to summarise the instances in which the ML model makes mistakes and the correlation between primary predictions and true labels. Following this, the LLM can transfer its acquired knowledge to suggest corrections for the ML model's predictions. Our experimental results on text analysis and the challenging molecular predictions show that \model improves the performance of a number of models by up to 39%.

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。

↑