Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Teyu Lin, Minghao Fan, Huaxun Huang, Zhirong Shen, Rongxin Wu

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.

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

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.

Paper Structure

This paper contains 34 sections, 6 equations, 5 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Rule-Based Methods
  4. Classification-Based Methods
  5. Generation-Based Methods
  6. Motivation
  7. Approach
  8. Overview
  9. Knowledge Base Construction
  10. Code Slicing
  11. System Dependency Graph Construction
  12. Code Slicing Generation
  13. Prompt Construction
  14. Discussion
  15. Evaluation
  16. ...and 19 more sections

Figures (5)

  • Figure 1: The motivating example where model serves as the target variable for data type inference.
  • Figure 2: The slices of Figure \ref{['fig:example code']} for TypePro, TypeGen and Tiger.
  • Figure 3: The Overview of TypePro.
  • Figure 4: The prompt generated for the example in Figure \ref{['fig:example code']}
  • Figure 5: Correct answer distribution between TypePro and baselines