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 2305.14264cs.CLcs.AI
收藏

基于大型语言模型上下文学习的主动学习原理

Active Learning Principles for In-Context Learning with Large Language Models

University of Sheffield(谢菲尔德大学);FAIR, Meta(Meta FAIR研究院)

Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu

AI总结:

本文将少样本上下文学习的示例选择视为基于池的主动学习问题,比较多种主动学习算法,发现基于相似性的方法最优,揭示了优先选择低不确定且与测试样本相似的高质量示例的原理。

摘要:

大型语言模型(LLMs)的显著进步大幅提升了少样本学习设置下的性能。通过仅使用少量被称为示例的标注样本,LLMs能够通过上下文学习有效掌握当前任务。然而,选择合适示例的过程在先前工作中鲜受关注。本文通过将此问题视为单次迭代的基于池的主动学习(AL)问题,解决了为少样本学习识别信息量最大示例的问题。我们的目标是研究AL算法如何作为上下文学习的有效示例选择方法。我们比较了基于不确定性、多样性和相似性的各种标准AL算法,并一致观察到后者优于包括随机采样在内的所有其他方法。值得注意的是,不确定性采样尽管在传统监督学习场景中表现成功,但在该背景下表现不佳。我们涉及GPT和OPT模型及24个分类和多选任务的广泛实验及分析明确表明,通过AL进行上下文示例选择优先考虑低不确定性且与测试样本相似的高质量示例。

英文摘要:

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively grasp the task at hand through in-context learning. However, the process of selecting appropriate demonstrations has received limited attention in prior work. This paper addresses the issue of identifying the most informative demonstrations for few-shot learning by approaching it as a pool-based Active Learning (AL) problem over a single iteration. Our objective is to investigate how AL algorithms can serve as effective demonstration selection methods for in-context learning. We compare various standard AL algorithms based on uncertainty, diversity, and similarity, and consistently observe that the latter outperforms all other methods, including random sampling. Notably, uncertainty sampling, despite its success in conventional supervised learning scenarios, performs poorly in this context. Our extensive experimentation involving a diverse range of GPT and OPT models across $24$ classification and multi-choice tasks, coupled with thorough analysis, unambiguously demonstrates that in-context example selection through AL prioritizes high-quality examples that exhibit low uncertainty and bear similarity to the test examples.

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。

↑