TypeScript and Python are two programming languages that support optional type annotations, which are useful but tedious to introduce and maintain. This has motivated automated type prediction: given an untyped program, produce a well-typed output program. Large language models (LLMs) are promising for type prediction, but there are challenges: fill-in-the-middle performs poorly, programs may not fit into the context window, generated types may not type check, and it is difficult to measure how well-typed the output program is. We address these challenges by building OpenTau, a search-based approach for type prediction that leverages large language models. We propose a new metric for type prediction quality, give a tree-based program decomposition that searches a space of generated types, and present fill-in-the-type fine-tuning for LLMs. We evaluate our work with a new dataset for TypeScript type prediction, and show that 47.4% of files type check (14.5% absolute improvement) with an overall rate of 3.3 type errors per file. All code, data, and models are available at: https://github.com/GammaTauAI/opentau.

翻译：TypeScript和Python是两种支持可选类型注解的编程语言，这一特性虽然实用但引入和维护较为繁琐。这促使了自动化类型预测的研究：给定一个无类型程序，生成类型正确的输出程序。大型语言模型（LLMs）在类型预测方面具有潜力，但面临挑战：中间填充方法表现不佳、程序可能超出上下文窗口、生成的类型可能无法通过类型检查、以及难以衡量输出程序的类型正确性。我们通过构建OpenTau——一种基于搜索且利用大型语言模型的类型预测方法——来应对这些挑战。我们提出了一种新的类型预测质量度量指标、一种基于树结构的程序分解方法以搜索生成类型的空间，以及面向LLM的类型填充微调方法。基于新构建的TypeScript类型预测数据集评估，我们实现了47.4%的文件通过类型检查（绝对提升14.5%），平均每个文件仅出现3.3个类型错误。所有代码、数据和模型均已开源：https://github.com/GammaTauAI/opentau。