1
25-070
Practical Applications of Large Language Models in Mining
Brad Gyngell
Hevi Pty Ltd, Sydney, Australia
Paul Culvenor
Hevi Pty Ltd, Brisbane, Australia
ABSTRACT
Large language models (LLMs) have generated a lot of hype
since ChatGPT was released in early 2023. In essence, they
allow people to interact with computer systems through
natural language and have the ability to generate highly
complex text, images and videos (Patil and Gudivada,
2024).
It is clear that this technology has significant potential,
however most mining companies have not yet found practi-
cal applications for it within their operations.
In this paper, we present a range of such applications
along with the tactical considerations associated with devel-
oping and implementing them. We have identified use
cases across a variety of operational and functional areas
within the mining industry and evaluated them based on
their potential business value and ease of implementation.
Firstly, we provide an overview of how LLMs work and
a review of how LLMs are being applied in other industries
to provide best practice inspiration for mining.
Next, we present a list of possible applications in min-
ing and a critical assessment of each use case. This section
also includes a technical deep dive into the different meth-
odologies for developing the technologies as well as an anal-
ysis of barriers to adoption within mining organizations.
Finally, we share a discussion of the potential path
forward for LLMs in mining and the impact they could
have on the industry. We analyze the potential differences
between early adopters and laggards in the artificial intel-
ligence (AI) space.
This research draws on interviews and surveys with
artificial intelligence experts as well as mining subject mat-
ter experts to connect cutting edge thought leadership with
the specific problems faced by our industry.
INTRODUCTION
The advent of various sectors, with ChatGPT’s release in
early 2023 marking a significant milestone demonstrated
an unprecedented ability to understand and generate
complex text, images, and videos through conversational
interfaces (Patil and Gudivada, 2024). This paper explores
the untapped potential of LLMs within the mining indus-
try, a sector yet to fully capitalize on these technological
advancements.
Despite the transformative possibilities LLMs pres-
ent, practical applications in mining operations remain
largely unexplored. Our research aims to bridge this gap
by presenting a suite of applications tailored to the min-
ing context. We assess these applications against two critical
dimensions: their potential business value and the ease of
implementation, providing a pragmatic guide for mining
companies considering the integration of LLMs into their
workflows.
The structure of this paper is designed to navigate the
reader through the intricacies of LLMs, from a founda-
tional understanding to specific industry applications. We
commence with a technical overview of LLMs, followed by
a review of their applications in other industries to inspire
best practices for mining. Subsequently, we delve into a
curated list of mining-specific applications, accompanied
by a thorough evaluation of each use case.
To ensure our findings are grounded in reality, we have
drawn upon insights from interviews and surveys with AI
experts and mining subject matter experts. This approach
allows us to align cutting-edge AI developments with the
unique challenges faced by the mining industry. By doing
so, we aim to illuminate a path forward for the adoption of
LLMs in mining, considering the strategic implications for
early adopters and the potential consequences for laggards
in the AI space.
25-070
Practical Applications of Large Language Models in Mining
Brad Gyngell
Hevi Pty Ltd, Sydney, Australia
Paul Culvenor
Hevi Pty Ltd, Brisbane, Australia
ABSTRACT
Large language models (LLMs) have generated a lot of hype
since ChatGPT was released in early 2023. In essence, they
allow people to interact with computer systems through
natural language and have the ability to generate highly
complex text, images and videos (Patil and Gudivada,
2024).
It is clear that this technology has significant potential,
however most mining companies have not yet found practi-
cal applications for it within their operations.
In this paper, we present a range of such applications
along with the tactical considerations associated with devel-
oping and implementing them. We have identified use
cases across a variety of operational and functional areas
within the mining industry and evaluated them based on
their potential business value and ease of implementation.
Firstly, we provide an overview of how LLMs work and
a review of how LLMs are being applied in other industries
to provide best practice inspiration for mining.
Next, we present a list of possible applications in min-
ing and a critical assessment of each use case. This section
also includes a technical deep dive into the different meth-
odologies for developing the technologies as well as an anal-
ysis of barriers to adoption within mining organizations.
Finally, we share a discussion of the potential path
forward for LLMs in mining and the impact they could
have on the industry. We analyze the potential differences
between early adopters and laggards in the artificial intel-
ligence (AI) space.
This research draws on interviews and surveys with
artificial intelligence experts as well as mining subject mat-
ter experts to connect cutting edge thought leadership with
the specific problems faced by our industry.
INTRODUCTION
The advent of various sectors, with ChatGPT’s release in
early 2023 marking a significant milestone demonstrated
an unprecedented ability to understand and generate
complex text, images, and videos through conversational
interfaces (Patil and Gudivada, 2024). This paper explores
the untapped potential of LLMs within the mining indus-
try, a sector yet to fully capitalize on these technological
advancements.
Despite the transformative possibilities LLMs pres-
ent, practical applications in mining operations remain
largely unexplored. Our research aims to bridge this gap
by presenting a suite of applications tailored to the min-
ing context. We assess these applications against two critical
dimensions: their potential business value and the ease of
implementation, providing a pragmatic guide for mining
companies considering the integration of LLMs into their
workflows.
The structure of this paper is designed to navigate the
reader through the intricacies of LLMs, from a founda-
tional understanding to specific industry applications. We
commence with a technical overview of LLMs, followed by
a review of their applications in other industries to inspire
best practices for mining. Subsequently, we delve into a
curated list of mining-specific applications, accompanied
by a thorough evaluation of each use case.
To ensure our findings are grounded in reality, we have
drawn upon insights from interviews and surveys with AI
experts and mining subject matter experts. This approach
allows us to align cutting-edge AI developments with the
unique challenges faced by the mining industry. By doing
so, we aim to illuminate a path forward for the adoption of
LLMs in mining, considering the strategic implications for
early adopters and the potential consequences for laggards
in the AI space.