The
advancement
of
Large
Language
Models
(LLMs)
has
led
to
their
widespread
use
across
a
broad
spectrum
tasks,
including
decision-making.
Prior
studies
have
compared
the
decision-making
abilities
LLMs
with
those
humans
from
psychological
perspective.
However,
these
not
always
properly
accounted
for
sensitivity
LLMs'
behavior
hyperparameters
and
variations
in
prompt.
In
this
study,
we
examine
performance
on
Horizon
task
studied
by
Binz
Schulz
(2023),
analyzing
how
respond
prompts
hyperparameters.
By
experimenting
three
OpenAI
language
models
possessing
different
capabilities,
observe
that
fluctuate
based
input
temperature
settings.
Contrary
previous
findings,
display
human-like
exploration–exploitation
tradeoff
after
simple
adjustments
Oeconomia Copernicana,
Год журнала:
2024,
Номер
15(2), С. 407 - 433
Опубликована: Июнь 30, 2024
Research
background:
AI
devices
and
robots
play
an
increasingly
important
role
in
consumers’
everyday
life,
by
accompanying
the
consumer
all
day
long.
This
presence
has
several
utilitarian
social
benefits,
but
at
same
time
optimal
functioning
of
requires
personal
information
from
consumer.
Purpose
article:
Starting
premise
that
people
share
more
with
friends,
we
have
tested
empirically
whether
emotional
behavior
can
evoke
emotions
relationship
between
consumers
their
devices,
leading
to
a
higher
self-disclosing
behavior.
Methods:
To
validate
proposed
hypotheses,
three
mediation
models
were
using
structural
equation
modelling
Smart-PLS
3.3.3,
based
on
data
collected
help
online
survey.
Findings
&
value
added:
We
prove
AI’s
increase
trust,
it
feelings
friendship
determine
perceived
control
over
shared
private
information,
thus
lower
threats
regarding
vulnerability
exposure
related
sharing
data.
These
results
implications
for
designing
consumer-AI
interactions.
Journal of Tourism and Gastronomy Studies,
Год журнала:
2024,
Номер
unknown
Опубликована: Март 30, 2024
ChatGPT
is
a
generative
artificial
intelligence
technology.
It
technology
that
becoming
more
widely
used.
This
research
aimed
to
identify
the
determinants
of
usage
in
tourism
and
hospitality
industry.
For
this
purpose,
systematic
literature
review
was
conducted,
six
were
identified.
These
are
experience
quality,
satisfaction,
interaction,
ethics,
reliability,
design
features.
determined
variables
affect
behavioral
intention
regarding
ChatGPT.
Within
scope
findings,
model
for
using
proposed
from
perspective
Technology
Acceptance
Model.
Determinants
use
industry
have
been
Relevant
articles
subjected
thematic
analysis
themes
determined.
These;
quality
experience,
reliability
In
research,
accommodation
sector
identified
recommendations
made.
The
advancement
of
Large
Language
Models
(LLMs)
has
led
to
their
widespread
use
across
a
broad
spectrum
tasks,
including
decision-making.
Prior
studies
have
compared
the
decision-making
abilities
LLMs
with
those
humans
from
psychological
perspective.
However,
these
not
always
properly
accounted
for
sensitivity
LLMs'
behavior
hyperparameters
and
variations
in
prompt.
In
this
study,
we
examine
performance
on
Horizon
task
studied
by
Binz
Schulz
(2023),
analyzing
how
respond
prompts
hyperparameters.
By
experimenting
three
OpenAI
language
models
possessing
different
capabilities,
observe
that
fluctuate
based
input
temperature
settings.
Contrary
previous
findings,
display
human-like
exploration–exploitation
tradeoff
after
simple
adjustments
