Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models
This addresses privacy and resource challenges for commercial companies using LLMs in specialized domains, though it is incremental as it builds on existing lightweight models with iterative fine-tuning.
The paper tackles the problem of large language models lacking domain-specific knowledge for question-answering in specialized domains, proposing the Self-Evolution framework that achieves a 174% higher performance score on domain-specific evaluations compared to a baseline model and an 18.6% average efficiency improvement in deployment.
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.