Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization

TL;DR

This paper systematically evaluates how system prompts, model scale, prompting strategy, and programming language influence the performance of instruction-tuned language models and code language models in code generation tasks.

Contribution

It provides a comprehensive analysis of the effects of system prompts on code generation performance across various model sizes, prompting strategies, and programming languages.

Findings

System prompt influence increases with model scale.

Few-shot prompting reduces prompt sensitivity.

Java models are more sensitive to prompt variations than Python.

Abstract

Instruction-tuned Language Models ILMs have become essential components of modern AI systems, demonstrating exceptional versatility across a wide range of natural language and reasoning tasks. Among their most impactful applications is code generation, where ILMs--commonly referred to as Code Language Models CLMs--have demonstrated remarkable capability. This strength stems from their defining feature: the use of explicit task instructions during fine-tuning, which enables them to bridge natural language and code by translating human intent into executable code. While much of their progress has been driven by advances in scaling laws and training methodologies, one critical aspect remains underexplored--the impact of system prompts on the performance of both general-purpose ILMs and specialized CLMs when instantiated to assist users with code generation activities. In this study, we take a first step toward bridging this gap by systematically evaluating how system prompts of varying instructional detail, along with model scale, prompting strategy, and programming language, affect ILMs and CLMs in code generation tasks. Our evaluation framework, spanning 120 model configurations, reveals that (1) the influence of system prompts increases with model scale; (2) few-shot prompting reduces this effect compared to zero-shot; and (3) programming language matters, with Java showing greater sensitivity to system prompt variations than Python.