按难易程度选示范样本，让大模型学得更全面
Curriculum Demonstration Selection for In-Context Learning
- 先分样本难易度，再从简单到复杂选示范
- 在3个数据集上9个模型表现均优于基线
- 特别适合提升模型解决难题的能力
大语言模型在少量示范下展现出强大的上下文学习能力。然而，如何选择示范样本以激发模型全部潜力仍是关键挑战。本文提出课程示范选择（CDS）方法，不只依赖相似性，还根据样本复杂度进行划分。遵循课程学习思想，从简单到复杂逐步选取示范样本，使所选样本覆盖广泛难度层次，帮助大模型在训练集中学习多样化复杂性。实验表明，CDS在三个基准测试上持续优于基线方法，对九种大模型均有显著提升，尤其在解决复杂问题时效果突出。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to elicit the full potential of LLMs. In this paper, we propose Curriculum Demonstration Selection (CDS), a novel demonstration selection method for ICL. Instead of merely using similarity, CDS additionally partitions samples by their complexity measurements. Following curriculum learning, CDS then selects demonstrations from easy to difficult. Thus the selected demonstrations cover a wide range of difficulty levels, enabling LLMs to learn from varied complexities within the training set. Experiments demonstrate that our CDS consistently outperforms baseline methods, achieving notable improvements across nine LLMs on three benchmarks. Moreover, CDS proves especially effective in enhancing LLM performance in solving challenging problems.
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。