TypePro: Boosting LLM-Based Type Inference via Inter-Procedural Slicing

TL;DR

TypePro enhances LLM-based type inference for dynamic languages by using inter-procedural code slicing to provide richer context, significantly improving accuracy over existing methods.

Contribution

It introduces inter-procedural slicing to supplement context for LLMs, enabling more accurate type inference in dynamic languages.

Findings

Achieved Top-1 EM rates of 88.9% on ManyTypes4Py and 86.6% on ManyTypes4TypeScript.

Improved Top-1 EM by 7.1 and 10.3 percentage points over the second-best approach.

Demonstrated effectiveness and robustness of TypePro through extensive experiments.

Abstract

Dynamic languages (such as Python and JavaScript) offer flexibility and simplified type handling for programming, but this can also lead to an increase in type-related errors and additional overhead for compile-time type inference. As a result, type inference for dynamic languages has become a popular research area. Existing approaches typically achieve type inference through static analysis, machine learning, or large language models (LLMs). However, current work only focuses on the direct dependencies of variables related to type inference as the context, resulting in incomplete contextual information and thus affecting the accuracy of type inference. To address this issue, this paper proposes a method called TypePro, which leverages LLMs for type inference in dynamic languages. TypePro supplements contextual information by conducting inter-procedural code slicing. Then, TypePro proposes a set of candidate complex types based on the structural information of data types implied in the slices, thereby addressing the lack of domain knowledge of LLMs. We conducted experiments on the ManyTypes4Py and ManyTypes4TypeScript datasets, achieving Top-1 exact match (EM) rates of 88.9% and 86.6%, respectively. Notably, TypePro improves the Top-1 Exact Match by 7.1 and 10.3 percentage points over the second-best approach, showing the effectiveness and robustness of TypePro.