可解释机器学习：用语言模型重新审视机器学习
Verbalized Machine Learning: Revisiting Machine Learning with Language Models
AI总结：
本文提出可解释机器学习（VML）框架，将ML模型参数空间约束为自然语言，通过LLM参数化的学习器和优化器解决回归、分类等问题，实现归纳偏置易编码、模型类自动选择、更新可解释的优势，并验证其有效性。
摘要：
受大型语言模型（LLMs）进展的启发，我们引入可解释机器学习（VML）框架。与通常在连续参数空间优化的传统机器学习（ML）模型不同，VML将参数空间限制为人类可解释的自然语言。这种约束带来函数近似的新视角：带文本提示的LLM可视为由文本提示参数化的函数。在此视角下，我们重新审视回归和分类等经典ML问题，发现这些问题可由LLM参数化的学习器和优化器解决。VML的主要优势包括：（1）易于编码归纳偏置：问题和假设类的先验知识可编码为自然语言并输入LLM参数化学习器；（2）自动模型类选择：优化器可基于数据和可解释先验知识自动选择模型类，并在训练中更新；（3）可解释的学习器更新：LLM参数化优化器可解释执行更新的原因。我们通过实验验证了VML的有效性，希望VML能成为实现更强可解释性的垫脚石。
英文摘要：
Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous parameter space, VML constrains the parameter space to be human-interpretable natural language. Such a constraint leads to a new perspective of function approximation, where an LLM with a text prompt can be viewed as a function parameterized by the text prompt. Guided by this perspective, we revisit classical ML problems, such as regression and classification, and find that these problems can be solved by an LLM-parameterized learner and optimizer. The major advantages of VML include (1) easy encoding of inductive bias: prior knowledge about the problem and hypothesis class can be encoded in natural language and fed into the LLM-parameterized learner; (2) automatic model class selection: the optimizer can automatically select a model class based on data and verbalized prior knowledge, and it can update the model class during training; and (3) interpretable learner updates: the LLM-parameterized optimizer can provide explanations for why an update is performed. We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
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。
