Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models

TL;DR

This paper introduces Self-Evolution, a novel iterative fine-tuning framework for lightweight domain-specific Q&A models based on large language models, significantly improving performance and operational efficiency in real-world applications.

Contribution

The paper presents a new framework for efficient domain-specific fine-tuning of lightweight LLMs, with a knowledge filtering strategy and successful deployment in industry.

Findings

Performance score 174% higher than baseline Qwen1.5-7B-Chat.

Achieved 22% higher performance than larger Qwen1.5-72B-Chat.

Improved operational efficiency by over 18.6% in real-world tasks.

Abstract

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge. Commercial companies face the dual challenges of privacy protection and resource constraints when involving LLMs for fine-tuning. This paper propose a novel framework, Self-Evolution, designed to address these issues by leveraging lightweight open-source LLMs through multiple iterative fine-tuning rounds. To enhance the efficiency of iterative fine-tuning, Self-Evolution employ a strategy that filters and reinforces the knowledge with higher value during the iterative process. We employed Self-Evolution on Qwen1.5-7B-Chat using 4,000 documents containing rich domain knowledge from China Mobile, achieving a performance score 174% higher on domain-specific question-answering evaluations than Qwen1.5-7B-Chat and even 22% higher than Qwen1.5-72B-Chat. Self-Evolution has been deployed in China Mobile's daily operation and maintenance for 117 days, and it improves the efficiency of locating alarms, fixing problems, and finding related reports, with an average efficiency improvement of over 18.6%. In addition, we release Self-Evolution framework code in https://github.com/Zero-Pointer/Self-Evolution.