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 2410.20008cs.CLcs.LG
收藏

逐层剖析：揭示多任务学习在指令微调大型语言模型中的发生位置

Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models

Institute for Language, Cognition and Computation, University of Edinburgh（爱丁堡大学语言、认知与计算研究所）；Nvidia Research（英伟达研究院）

Zheng Zhao, Yftah Ziser, Shay B. Cohen

备注：
Accepted to EMNLP 2024
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对指令微调 LLM 在何处保留任务知识的问题，本文用矩阵分析工具比较60余个 NLP 任务的层表征，定位通用表征转向任务表征的位置。

摘要：

在多种多样的任务上微调预训练大型语言模型（LLM），已成为构建能够解决各类自然语言处理（NLP）任务的模型的常用方法。然而，这些模型在何处以及在多大程度上保留任务特定知识，仍基本未被探索。本研究考察了预训练 LLM 中编码的任务特定信息，以及指令微调对其在超过60个多样化 NLP 任务上的表征所产生的影响。我们使用一组矩阵分析工具，检验预训练 LLM 与指令微调 LLM 在存储任务特定信息方式上的差异。研究结果表明，尽管部分任务已经编码在预训练 LLM 中，但其他任务则从指令微调中大幅受益。此外，我们还准确定位了模型从高层通用表征转向更具任务导向表征的若干层。这一发现拓展了我们对 LLM 治理机制的理解，并有助于推动未来在参数高效迁移学习和多任务学习领域的研究。

英文摘要：

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models retain task-specific knowledge remains largely unexplored. This study investigates the task-specific information encoded in pre-trained LLMs and the effects of instruction tuning on their representations across a diverse set of over 60 NLP tasks. We use a set of matrix analysis tools to examine the differences between the way pre-trained and instruction-tuned LLMs store task-specific information. Our findings reveal that while some tasks are already encoded within the pre-trained LLMs, others greatly benefit from instruction tuning. Additionally, we pinpointed the layers in which the model transitions from high-level general representations to more task-oriented representations. This finding extends our understanding of the governing mechanisms of LLMs and facilitates future research in the fields of parameter-efficient transfer learning and multi-task learning.

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。

↑