LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan

TL;DR

This paper benchmarks various large language models for local life services, demonstrating that smaller models can achieve comparable performance to larger ones through fine-tuning and workflows, thus enabling practical deployment.

Contribution

It establishes a comprehensive benchmark for LLMs in local services and explores optimization techniques like fine-tuning and agent workflows for better efficiency.

Findings

A 7B model can match a 72B model's performance.

Fine-tuning improves model effectiveness in local service tasks.

Optimized models are more feasible for real-world deployment.

Abstract

Large language models (LLMs) have exhibited remarkable capabilities and achieved significant breakthroughs across various domains, leading to their widespread adoption in recent years. Building on this progress, we investigate their potential in the realm of local life services. In this study, we establish a comprehensive benchmark and systematically evaluate the performance of diverse LLMs across a wide range of tasks relevant to local life services. To further enhance their effectiveness, we explore two key approaches: model fine-tuning and agent-based workflows. Our findings reveal that even a relatively compact 7B model can attain performance levels comparable to a much larger 72B model, effectively balancing inference cost and model capability. This optimization greatly enhances the feasibility and efficiency of deploying LLMs in real-world online services, making them more practical and accessible for local life applications.