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 2408.11546cs.CLcs.AIcs.LG
收藏

上下文学习中的记忆现象

Memorization in In-Context Learning

University of Arizona(亚利桑那大学)

Shahriar Golchin, Mihai Surdeanu, Steven Bethard, Eduardo Blanco, Ellen Riloff

AI总结:

本研究首次揭示了上下文学习(ICL)通过引出训练数据记忆来提升大型语言模型性能,发现示例引出的记忆水平与下游任务性能存在强相关性,并质疑了模型成功的真正泛化程度。

摘要:

上下文学习(ICL)已被证明是一种无需额外训练即可提升大型语言模型(LLMs)性能的有效策略。然而,这种性能提升背后的确切机制仍不清楚。本研究首次展示了ICL如何引出记忆的训练数据,并探讨了在各种ICL机制(零样本、少样本和多样本)下,这种记忆与下游任务性能之间的相关性。我们最显著的发现包括:(1)在大多数情况下,与零样本学习相比,ICL显著引出了记忆;(2)不带标签的示例是引出记忆的最有效元素;(3)当少样本机制中引出的记忆达到高水平(约40%)时,ICL能提升性能;(4)当ICL优于零样本学习时,性能与记忆之间存在非常强的相关性。总体而言,我们的研究揭示了记忆作为影响ICL的新因素,提出了一个重要问题:LLMs在多大程度上真正从ICL的示例中泛化,其成功又有多少归因于记忆?

英文摘要:

In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mechanism behind this performance improvement remains unclear. This study is the first to show how ICL surfaces memorized training data and to explore the correlation between this memorization and performance on downstream tasks across various ICL regimes: zero-shot, few-shot, and many-shot. Our most notable findings include: (1) ICL significantly surfaces memorization compared to zero-shot learning in most cases; (2) demonstrations, without their labels, are the most effective element in surfacing memorization; (3) ICL improves performance when the surfaced memorization in few-shot regimes reaches a high level (about 40%); and (4) there is a very strong correlation between performance and memorization in ICL when it outperforms zero-shot learning. Overall, our study uncovers memorization as a new factor impacting ICL, raising an important question: to what extent do LLMs truly generalize from demonstrations in ICL, and how much of their success is due to memorization?

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。

↑