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 2503.03705cs.CLcs.LG
收藏

通过泛化增强大语言模型的知识学习

Enhancing LLM Knowledge Learning through Generalization

Mingkang Zhu, Xi Chen, Zhongdao Wang, Bei Yu, Hengshuang Zhao, Jiaya Jia

AI总结:

本研究提出通过格式数据增强和锐度感知最小化优化器,增强大语言模型在多样化上下文中的知识预测泛化能力,从而提升持续预训练和指令微调中的知识获取效果。

摘要:

随着大语言模型(LLMs)在各类应用中的部署日益广泛,如何将这些模型忠实地整合不断演变的事实知识仍然是一个关键挑战。在改写数据上进行持续预训练已被经验性地证明能够增强知识获取。然而,这种方法往往成本高昂且不可靠,因为它依赖于外部模型或人工进行改写,并且可能无意中改变事实内容。在本工作中,我们假设并通过实验证明,大语言模型在给定多样化的改写上下文时持续预测相同事实知识标记的能力,与其通过问答提取该知识的能力呈正相关。基于这一观点,并旨在提高对多样化改写上下文的泛化能力,我们引入了两种策略来增强大语言模型在给定不同上下文时预测相同知识标记的能力,从而增强知识获取。首先,我们提出了基于格式的数据增强方法,该方法通过改变文档格式而非内容来使传达相同知识的文档多样化,从而保持事实完整性。其次,我们采用锐度感知最小化作为优化器,以更好地改善泛化能力。大量实验表明,我们的方法在持续预训练和指令微调中均有效,并且与改写数据结合使用可获得进一步的提升。

英文摘要:

As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge. Continued pre-training on paraphrased data has shown empirical promise for enhancing knowledge acquisition. However, this approach is often costly and unreliable, as it relies on external models or manual effort for rewriting, and may inadvertently alter the factual content. In this work, we hypothesize and empirically show that an LLM's ability to continually predict the same factual knowledge tokens given diverse paraphrased contexts is positively correlated with its capacity to extract that knowledge via question-answering. Based on this view and aiming to improve generalization to diverse paraphrased contexts, we introduce two strategies to enhance LLMs' ability to predict the same knowledge tokens given varied contexts, thereby enhancing knowledge acquisition. First, we propose formatting-based data augmentation, which diversifies documents conveying the same knowledge by altering document formats rather than their content, thereby preserving factual integrity. Second, we adopt sharpness-aware minimization as the optimizer to better improve generalization. Extensive experiments demonstrate our methods' effectiveness in both continued pre-training and instruction tuning, and further gains can be achieved by combining with paraphrased data.

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。

↑