MiningGPT -- A Domain-Specific Large Language Model for the Mining Industry

TL;DR

MiningGPT is a specialized large language model tailored for the mining industry, demonstrating improved domain knowledge and understanding compared to general models, thus supporting industry-specific applications.

Contribution

This work introduces MiningGPT, a 7B parameter domain-specific LLM for mining, showing significant knowledge gains over a general instruction-following model.

Findings

MiningGPT achieved 14% higher domain knowledge test scores.

MiningGPT outperforms general models in mining-specific tasks.

The model supports industry-specific language understanding.

Abstract

Recent advancements of generative LLMs (Large Language Models) have exhibited human-like language capabilities but have shown a lack of domain-specific understanding. Therefore, the research community has started the development of domain-specific LLMs for many domains. In this work we focus on discussing how to build mining domain-specific LLMs, as the global mining industry contributes significantly to the worldwide economy. We report on MiningGPT, a mining domain-specific instruction-following 7B parameter LLM model which showed a 14\% higher mining domain knowledge test score as compared to its parent model Mistral 7B instruct.