AI模型组合性学习综述：理论与实践
A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices
AI总结：
本文系统综述了AI模型组合性学习的理论定义、评估基准、计算模型及与认知研究的联系，重点分析语言与视觉模型的前沿组合能力并指出未来研究方向。
摘要：
组合性学习，即掌握组合基本概念并构建更复杂概念的能力，对人类认知至关重要，尤其是在人类语言理解和视觉感知方面。这一概念与对未观察情境的泛化能力密切相关。尽管组合性在智能中具有不可或缺的作用，但目前缺乏系统的理论和实验研究方法，使得分析计算模型的组合性学习能力变得困难。本文综述了关于AI模型组合性学习的文献及其与认知研究的联系。我们识别了认知和语言研究中组合性的抽象概念，并将其与语言和视觉模型在组合推理中所面临的计算挑战联系起来。我们概述了形式化定义、任务、评估基准、各类计算模型以及理论发现。我们的主要关注点是语言基准以及语言与视觉的结合，尽管仅计算机视觉领域就有大量关于组合概念学习的研究。我们还涵盖了关于大语言模型的现代研究，以更深入地理解最先进AI模型所展现的前沿组合能力，并指出未来研究的重要方向。
英文摘要：
Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to generalization over unobserved situations. Despite its integral role in intelligence, there is a lack of systematic theoretical and experimental research methodologies, making it difficult to analyze the compositional learning abilities of computational models. In this paper, we survey the literature on compositional learning of AI models and the connections made to cognitive studies. We identify abstract concepts of compositionality in cognitive and linguistic studies and connect these to the computational challenges faced by language and vision models in compositional reasoning. We overview the formal definitions, tasks, evaluation benchmarks, various computational models, and theoretical findings. Our primary focus is on linguistic benchmarks and combining language and vision, though there is a large amount of research on compositional concept learning in the computer vision community alone. We cover modern studies on large language models to provide a deeper understanding of the cutting-edge compositional capabilities exhibited by state-of-the-art AI models and pinpoint important directions for future research.
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。
