Large Language Model-Aware In-Context Learning for Code Generation

doi:10.1145/3715908

Large Language Model-Aware In-Context Learning for Code Generation

2025-08-14

0

OA

AI

DOI：10.1145/3715908

Original request for help

Save

Abstract

En 中文

Large Language Models (LLMs) have shown impressive In-Context Learning (ICL) ability in code generation. LLMs take a prompt context consisting of a few demonstration examples and a new requirement as input, and output new programs without any parameter update. Existing studies have found that the performance of ICL-based code generation heavily depends on the quality of demonstration examples and thus arises research on selecting demonstration examples: given a new requirement, a few demonstration examples are selected from a candidate pool, where LLMs are expected to learn the pattern hidden in these selected demonstration examples. Existing approaches are mostly based on heuristics or randomly selecting examples. However, the distribution of randomly selected examples usually varies greatly, making the performance of LLMs less robust. The heuristics retrieve examples by only considering textual similarities of requirements, leading to sub-optimal performance.

Keywords:

In-Context Learning

Code Generation

Large Language Models

Demonstration Example Selection

Prompt Engineering

Large Language Model-Aware In-Context Learning for Code Generation

Abstract

Journal

Organization