Explainable AI Chatbots Towards XAI ChatGPT: A Review
Heliyon,
Journal Year:
2025,
Volume and Issue:
11(2), P. e42077 - e42077
Published: Jan. 1, 2025
Advances
in
artificial
intelligence
(AI)
have
had
a
major
impact
on
natural
language
processing
(NLP),
even
more
so
with
the
emergence
of
large-scale
models
like
ChatGPT.
This
paper
aims
to
provide
critical
review
explainable
AI
(XAI)
methodologies
for
chatbots,
particular
focus
Its
main
objectives
are
investigate
applied
methods
that
improve
explainability
identify
challenges
and
limitations
within
them,
explore
future
research
directions.
Such
goals
emphasize
need
transparency
interpretability
systems
build
trust
users
allow
accountability.
While
integrating
such
interdisciplinary
methods,
as
hybrid
combining
knowledge
graphs
ChatGPT,
enhancing
explainability,
they
also
highlight
industry
needs
user-centred
design.
will
be
followed
by
discussion
balance
between
performance,
then
role
human
judgement,
finally
verifiable
AI.
These
avenues
through
which
insights
can
used
guide
development
transparent,
reliable
efficient
chatbots.
Language: Английский
A Framework for Integrating Vision Transformers with Digital Twins in Industry 5.0 Context
Machines,
Journal Year:
2025,
Volume and Issue:
13(1), P. 36 - 36
Published: Jan. 7, 2025
The
transition
from
Industry
4.0
to
5.0
gives
more
prominence
human-centered
and
sustainable
manufacturing
practices.
This
paper
proposes
a
conceptual
design
framework
based
on
Vision
Transformers
(ViTs)
digital
twins,
meet
the
demands
of
5.0.
ViTs,
known
for
their
advanced
visual
data
analysis
capabilities,
complement
simulation
optimization
capabilities
which
in
turn
can
enhance
predictive
maintenance,
quality
control,
human–machine
symbiosis.
applied
is
capable
analyzing
multidimensional
data,
integrating
operational
streams
real-time
tracking
application
decision
making.
Its
main
characteristics
are
anomaly
detection,
analytics,
adaptive
optimization,
line
with
objectives
sustainability,
resilience,
personalization.
Use
cases,
including
maintenance
demonstrate
higher
efficiency,
waste
reduction,
reliable
operator
interaction.
In
this
work,
emergent
role
ViTs
twins
development
intelligent,
dynamic,
human-centric
industrial
ecosystems
discussed.
Language: Английский
AI for Decision Support: Balancing Accuracy, Transparency, and Trust Across Sectors
Information,
Journal Year:
2024,
Volume and Issue:
15(11), P. 725 - 725
Published: Nov. 11, 2024
This
study
seeks
to
understand
the
key
success
factors
that
underpin
efficiency,
transparency,
and
user
trust
in
automated
decision
support
systems
(DSS)
leverage
AI
technologies
across
industries.
The
aim
of
this
is
facilitate
more
accurate
decision-making
with
such
AI-based
DSS,
as
well
build
through
need
for
visibility
explainability
by
increasing
acceptance.
primarily
examines
nature
DSS
adoption
challenges
maintaining
system
transparency
improving
accuracy.
results
provide
practical
guidance
professionals
decision-makers
develop
AI-driven
are
not
only
effective
but
also
trusted
users.
important
gain
insight
into
how
artificial
intelligence
fits
combines
decision-making,
which
can
be
derived
from
research
when
thinking
about
embedding
ethical
standards.
Language: Английский