用教育心理学理论分析大模型如何通过上下文示例学习
Investigating the Zone of Proximal Development of Language Models for In-Context Learning
- 用最近发展区理论衡量大模型在上下文学习中的潜力
- 提出新方法预测模型最可能受益的示例类型
- 可用于优化推理效率和训练课程设计
本文引入学习分析框架，基于教育心理学中的最近发展区（ZPD）理论，分析大语言模型（LLMs）在上下文学习（ICL）中的行为。ZPD描述了学习者独立完成与在支持下仍无法完成任务之间的差距。我们通过模型在有无ICL时对单个示例的表现，量化其ZPD，并提出项目反应理论（IRT）模型来预测模型的区域分布。研究揭示了ICL的复杂行为特征，提供了理解与利用该技术的新视角。最后，我们展示了该框架在推理和微调中的应用：(1) 通过预测模型的最近发展区，仅对最可能受益的查询应用ICL，实现推理成本与性能的更好平衡；(2) 提出一种类人课程微调策略，优先选择模型处于其ZPD内的示例，提升性能，并通过训练动态分析解释其有效性。
原文摘要 · Abstract (English)
In this paper, we introduce a learning analytics framework to analyze the in-context learning (ICL) behavior of large language models (LLMs) through the lens of the Zone of Proximal Development (ZPD), an established theory in educational psychology. ZPD delineates the space between what a learner is capable of doing unsupported and what the learner cannot do even with support. We adapt this concept to ICL, measuring the ZPD of LLMs based on model performance on individual examples with and without ICL. Furthermore, we propose an item response theory (IRT) model to predict the distribution of zones for LLMs. Our findings reveal a series of intricate and multifaceted behaviors of ICL, providing new insights into understanding and leveraging this technique. Finally, we demonstrate how our framework can enhance LLM in both inference and fine-tuning scenarios: (1) By predicting a model's zone of proximal development, we selectively apply ICL to queries that are most likely to benefit from demonstrations, achieving a better balance between inference cost and performance; (2) We propose a human-like curriculum for fine-tuning, which prioritizes examples within the model's ZPD. The curriculum results in improved performance, and we explain its effectiveness through an analysis of the training dynamics of LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。