Verbalized Machine Learning: Revisiting Machine Learning with Language Models

TL;DR

This paper introduces verbalized machine learning (VML), a framework where language models are used as interpretable, human-readable function approximators for classical ML tasks, enabling easier encoding of prior knowledge and interpretability.

Contribution

The paper presents VML, a novel approach that constrains ML models to natural language, allowing for interpretability, automatic model selection, and incorporation of prior knowledge.

Findings

VML effectively solves regression and classification tasks.

It enables encoding of prior knowledge in natural language.

The approach provides interpretable model updates.

Abstract

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.