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 2602.04212cs.CLcs.AI
收藏

语言模型在上下文学习的表示使用上面临困难

Language Models Struggle to Use Representations Learned In-Context

Brown University(布朗大学);Google Research(谷歌研究);New York University(纽约大学);Google DeepMind(谷歌DeepMind)

Michael A. Lepori, Tal Linzen, Ann Yuan, Katja Filippova

AI总结:

研究探讨了语言模型是否能利用上下文学习的表示完成简单下游任务,发现开放权重模型在处理新语义表示时存在困难,即使它们在潜在表示中编码了这些语义。

摘要:

尽管大型语言模型(LLMs)在各种任务上取得了巨大成功,但它们似乎未能实现人工智能研究的更高目标:创建一个能够适应部署后完全新上下文的人工系统。一个重要步骤是创建能够从上下文中学到丰富数据表示的系统,并灵活地部署这些表示以完成目标。最近,Park等人(2024)证明当前LLMs确实能够从上下文中学到这样的表示(即上下文表示学习)。本研究探讨LLMs是否能利用这些表示完成简单下游任务。我们首先评估开放式权重LLMs是否能使用上下文表示进行下一个标记预测,然后通过一个新任务“适应性世界建模”来探测模型。在两项任务中,我们发现开放式权重LLMs在部署上下文定义的新语义表示时存在困难,即使它们在潜在表示中编码了这些语义。此外,我们评估了闭源、最先进的推理模型在适应性世界建模任务上的表现,证明即使是最先进的LLMs也无法可靠地利用上下文中的新模式。整体而言,本研究旨在启发新的方法,鼓励模型不仅编码上下文中的信息,而且以支持灵活部署的方式进行编码。

英文摘要:

Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its behavior to radically new contexts upon deployment. One important step towards this goal is to create systems that can induce rich representations of data that are seen in-context, and then flexibly deploy these representations to accomplish goals. Recently, Park et al. (2024) demonstrated that current LLMs are indeed capable of inducing such representation from context (i.e., in-context representation learning). The present study investigates whether LLMs can use these representations to complete simple downstream tasks. We first assess whether open-weights LLMs can use in-context representations for next-token prediction, and then probe models using a novel task, adaptive world modeling. In both tasks, we find evidence that open-weights LLMs struggle to deploy representations of novel semantics that are defined in-context, even if they encode these semantics in their latent representations. Furthermore, we assess closed-source, state-of-the-art reasoning models on the adaptive world modeling task, demonstrating that even the most performant LLMs cannot reliably leverage novel patterns presented in-context. Overall, this work seeks to inspire novel methods for encouraging models to not only encode information presented in-context, but to do so in a manner that supports flexible deployment of this information.

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。

↑