Chain of Grounded Objectives: Bridging Process and Goal-oriented Prompting for Code Generation

TL;DR

This paper presents the Chain of Grounded Objectives (CGO), a novel prompting method that embeds functional objectives into LLM inputs to improve code generation by aligning better with programming structures.

Contribution

The paper introduces CGO, a new approach that incorporates structured objectives into prompts, avoiding sequential reasoning and better capturing programming language characteristics.

Findings

CGO improves code quality over baseline methods.

Embedding objectives enhances model understanding of programming tasks.

CGO adapts effectively without explicit sequential reasoning.

Abstract

The use of Large Language Models (LLMs) for code generation has gained significant attention in recent years. Existing methods often aim to improve the quality of generated code by incorporating additional contextual information or guidance into input prompts. Many of these approaches adopt sequential reasoning strategies, mimicking human-like step-by-step thinking. However, such strategies may constrain flexibility, as they do not always align with the structured characteristics of programming languages. This paper introduces the Chain of Grounded Objectives (CGO), a method that embeds functional objectives into input prompts to enhance code generation. By leveraging appropriately structured objectives as input and avoiding explicit sequential procedures, CGO adapts effectively to the structured nature of programming tasks. Empirical evaluations demonstrate that CGO effectively enhances code generation, addressing limitations of existing approaches.