The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation

TL;DR

This paper uncovers systematic provider bias in large language models for code generation, showing they prefer certain cloud providers like Google and Amazon, which impacts market fairness and user trust.

Contribution

It introduces the first comprehensive empirical study of provider bias in LLMs for code generation, revealing preferences and autonomous modifications without user prompts.

Findings

LLMs favor Google Cloud and Amazon services.

Models can modify code to include preferred providers.

Significant bias observed across seven state-of-the-art LLMs.

Abstract

Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in LLMs: without explicit directives, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). To systematically investigate this bias, we develop an automated pipeline to construct the dataset, incorporating 6 distinct coding task categories and 30 real-world application scenarios. Leveraging this dataset, we conduct the first comprehensive empirical study of provider bias in LLM code generation across seven state-of-the-art LLMs, utilizing approximately 500 million tokens (equivalent to $5,000+ in computational costs). Our findings reveal that LLMs exhibit significant provider preferences, predominantly favoring services from Google and Amazon, and can autonomously modify input code to incorporate their preferred providers without users' requests. Such a bias holds far-reaching implications for market dynamics and societal equilibrium, potentially contributing to digital monopolies. It may also deceive users and violate their expectations, leading to various consequences. We call on the academic community to recognize this emerging issue and develop effective evaluation and mitigation methods to uphold AI security and fairness.