用大模型根据数据特征自动推荐模型和超参，省去调参成本。
LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection
- 将数据转为可读元信息，让大模型基于上下文推荐模型与超参。
- 在真实与合成数据上表现接近搜索方法，零样本即有效。
- 适合想快速选型但缺乏调参经验的研究者或工程师。
模型与超参数选择是机器学习中的关键挑战，通常依赖专家直觉或昂贵的自动化搜索。本文探究大语言模型（LLMs）能否作为上下文元学习器完成此任务。通过将每个数据集转化为可解释的元信息，我们提示大模型推荐模型族和超参数。研究了两种提示策略：(1) 仅依赖预训练知识的零样本模式；(2) 加入过往任务中模型表现示例的元信息增强模式。在合成与真实世界基准上，结果表明，大模型能利用数据元信息推荐出具有竞争力的模型与超参数，且无需搜索；元信息增强带来的性能提升证明其具备上下文元学习能力。这些结果揭示了大模型作为轻量、通用的模型选择与超参数优化助手的巨大潜力。
原文摘要 · Abstract (English)
Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether large language models (LLMs) can act as in-context meta-learners for this task. By converting each dataset into interpretable metadata, we prompt an LLM to recommend both model families and hyperparameters. We study two prompting strategies: (1) a zero-shot mode relying solely on pretrained knowledge, and (2) a meta-informed mode augmented with examples of models and their performance on past tasks. Across synthetic and real-world benchmarks, we show that LLMs can exploit dataset metadata to recommend competitive models and hyperparameters without search, and that improvements from meta-informed prompting demonstrate their capacity for in-context meta-learning. These results highlight a promising new role for LLMs as lightweight, general-purpose assistants for model selection and hyperparameter optimization.
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。