Emergency
response
missions
require
rapid
and
accurate
information
processing
in
noisy,
chaotic
environments
where
oral
communications
present
significant
challenges,
leading
to
cognitive
overload
impaired
decision-making.
Augmented
Reality
(AR)
Large
Language
Models
(LLMs)
have
shown
potential
enhancing
situational
awareness
by
integrating
digital
data
with
the
physical
world
improving
dialogue
management.
However,
effectively
synthesizing
these
technologies
into
a
system
that
aids
first
responders
real-time
remains
challenge,
clear
need
for
research
validate
their
impact
on
clarity
coordination
of
during
high-pressure
missions.
This
study
investigates
integration
AR
LLMs
emergency
response,
focusing
controlling
load
related
communications.
Utilizing
AR's
capability
overlay
critical
onto
LLMs'
advanced
logic
reasoning,
aims
develop
an
AI
co-agent
aiding
audio
dialogue-based
tasks
high-risk
A
customized
system,
incorporating
Microsoft
HoloLens2
monitoring,
was
tested
participants
human
factor
experiment
(N=30).
The
2x2
factorial
evaluated
effects
LLM
assistance
performance
load.
Results
showed
notable
improvements
task
accuracy
reduced
load,
demonstrating
effectiveness
supporting
operations.
findings
underline
importance
further
this
technologically
innovative
area,
crucial
optimizing
strategies.
Journal of Engineering Design,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 23
Published: May 20, 2024
Machine
learning
has
been
widely
used
in
design
activities,
enabling
more
informed
decision-making.
However,
high-performance
machine
models,
often
referred
to
as
'black-box',
result
a
lack
of
explainability
regarding
predictions.
The
absence
erodes
the
trust
between
designers
and
these
models
hinders
human-machine
collaboration
for
desirable
decisions.
Explainable
AI
focuses
on
creating
explanations
that
are
accessible
comprehensible
stakeholders,
thereby
improving
explainability.
A
recent
advancement
field
explainable
involves
leveraging
domain-specific
knowledge
via
graph.
Additionally,
advent
large
language
like
ChatGPT,
acclaimed
their
ability
output
domain
knowledge,
perform
complex
processing,
support
seamless
end-user
interaction,
potential
expand
horizons
AI.
Inspired
by
developments,
we
propose
novel
hybrid
method
synergizes
ChatGPT
graph
augment
post-hoc
context.
outcome
is
generation
contextual
meaningful
explanations,
with
added
possibility
further
interaction
uncover
deeper
insights.
effectiveness
proposed
illustrated
through
case
study
customer
segmentation.