Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

2026-09-03

AI Summary

该研究通过训练将自然语言规范转换为本地神经函数，解决了规则难以实现文本功能及远程模型成本高、延迟大等问题。

Abstract

Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and dependency on a provider. We present compile by training, which turns a natural-language specification into a reusable neural function. At compile time, teacher models generate task-specific examples that are used to train a small adapter for a compact interpreter. The resulting function runs without the teachers and can be stored, versioned, and composed like ordinary software. On FuzzyBench-Hard, a subset on which the Program-as-Weights fast compiler produced no exact matches, compile by training reaches 83.6% semantic accuracy. This higher accuracy comes with a higher compile-time cost: roughly a minute rather than seconds for the fast compiler. We deploy the compiler in a public interactive service and demonstrate compiled functions in a multi-site website helper, a language-controlled 3D avatar, and a bidirectional English-Claudish translator.

Problem

• natural-language specifications
• local neural functions
• recurring text functions
• large remote model
• cost and latency

Innovation

• natural-language specification
• neural function
• small adapter
• compact interpreter
• semantic accuracy