Large
language
models
(LLMs)
can
help
writers
build
story
worlds
by
generating
world
elements,
such
as
factions,
characters,
and
locations.
However,
making
sense
of
many
generated
elements
be
overwhelming.
Moreover,
if
the
user
wants
to
precisely
control
aspects
that
are
difficult
specify
verbally,
prompting
alone
may
insufficient.
We
introduce
Patchview,
a
customizable
LLM-powered
system
visually
aids
worldbuilding
allowing
users
interact
with
concepts
through
physical
metaphor
magnets
dust.
Elements
in
Patchview
dragged
closer
high
relevance,
facilitating
sensemaking.
The
also
steer
generation
verbally
elusive
indicating
desired
position
element
between
concepts.
When
disagrees
LLM's
visualization
generation,
they
correct
those
repositioning
element.
These
corrections
used
align
future
behaviors
user's
perception.
With
study,
we
show
supports
sensemaking
steering
exploration
during
process.
provides
insights
on
how
visual
representation
sensemake,
steer,
generative
AI
model
intentions.
In
our
era
of
rapid
technological
advancement,
the
research
landscape
for
writing
assistants
has
become
increasingly
fragmented
across
various
communities.
We
seek
to
address
this
challenge
by
proposing
a
design
space
as
structured
way
examine
and
explore
multidimensional
intelligent
interactive
assistants.
Through
large
community
collaboration,
we
five
aspects
assistants:
task,
user,
technology,
interaction,
ecosystem.
Within
each
aspect,
define
dimensions
(i.e.,
fundamental
components
an
aspect)
codes
potential
options
dimension)
systematically
reviewing
115
papers.
Our
aims
offer
researchers
designers
practical
tool
navigate,
comprehend,
compare
possibilities
assistants,
aid
in
envisioning
new
The Journal of Creative Behavior,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 10, 2025
ABSTRACT
Artificial
intelligence
(AI)
systems
capable
of
generating
creative
outputs
are
reshaping
our
understanding
creativity.
This
shift
presents
an
opportunity
for
creativity
researchers
to
reevaluate
the
key
components
process.
In
particular,
advanced
capabilities
AI
underscore
importance
studying
internal
processes
paper
explores
neurobiological
machinery
that
underlies
these
and
describes
experiential
component
It
is
concluded
although
products
artificial
human
can
be
similar,
different.
The
also
discusses
how
may
negatively
affect
creativity,
such
as
development
skills,
authenticity
diversity
ideas.
SSRN Electronic Journal,
Год журнала:
2023,
Номер
unknown
Опубликована: Янв. 1, 2023
This
study
investigates
the
capability
of
generative
artificial
intelligence
(AI)
in
creating
innovative
business
solutions
compared
to
human
crowdsourcing
methods.
We
initiated
a
challenge
focused
on
sustainable,
circular
economy
opportunities.
The
attracted
diverse
range
solvers
from
myriad
countries
and
industries.
Simultaneously,
we
employed
GPT-4
generate
AI
using
three
different
prompt
levels,
each
calibrated
simulate
distinct
crowd
expert
personas.
145
evaluators
assessed
randomized
selection
10
out
234
solutions,
total
1,885
evaluator-solution
pairs.
Results
showed
comparable
quality
between
AI-generated
solutions.
However,
ideas
were
perceived
as
more
novel,
whereas
delivered
better
environmental
financial
value.
use
natural
language
processing
techniques
rich
solution
text
show
that
although
cover
similar
industries
application,
exhibit
greater
semantic
diversity.
connection
diversity
novelty
is
stronger
suggesting
differences
how
created
by
humans
or
detected
evaluators.
illuminates
potential
limitations
both
solve
complex
organizational
problems
sets
groundwork
for
possible
integrative
human-AI
approach
problem-solving.
Collaboration
has
been
shown
to
enhance
creativity,
leading
more
innovative
and
effective
outcomes.
While
previous
research
explored
the
abilities
of
Large
Language
Models
(LLMs)
serve
as
co-creative
partners
in
tasks
like
writing
poetry
or
creating
narratives,
collaborative
potential
LLMs
humor-rich
culturally
nuanced
domains
remains
an
open
question.
To
address
this
gap,
we
conducted
a
user
study
explore
co-creating
memes
-
humor-driven
specific
form
creative
expression.
We
with
three
groups
50
participants
each:
human-only
group
without
AI
assistance,
human-AI
collaboration
interacting
state-of-the-art
LLM
model,
AI-only
where
autonomously
generated
memes.
assessed
quality
through
crowdsourcing,
each
meme
rated
on
humor,
shareability.
Our
results
showed
that
assistance
increased
number
ideas
reduced
effort
felt.
However,
it
did
not
improve
when
humans
collaborated
LLM.
Interestingly,
created
entirely
by
performed
better
than
both
all
areas
average.
looking
at
top-performing
memes,
human-created
ones
were
while
collaborations
stood
out
creativity
These
findings
highlight
complexities
tasks.
can
boost
productivity
create
content
appeals
broad
audience,
human
crucial
for
connects
deeper
level.
Research Square (Research Square),
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 14, 2025
Abstract
The
work
in
this
paper
investigates
(a)
the
(emerging)
creative
self-perceptions
of
GenAI
chatbots,
(b)
their
potential,
(c)
ability
to
self-assess
creativity
own
outcomes
and
that
peers,
(d)
how
can
be
improved.
To
end,
an
exploratory
study
was
implemented
involving
three
popular
commercial
chatbots:
ChatGPT
(GPT-4o
-
paid)
by
OpenAI,
Claude
(3.5
Sonnet
Anthropic
Gemini
(1.5
Flash
free)
Google.
included
four
phases
employed
well-established
methods
tools
from
scientific
domain
(human)
research,
including
Short
Scale
Creative
Self
(SSCS)
questionnaire,
a
verbal
test
convergent-integrative
thought
Evaluation
Potential
Creativity
(EPoC)
battery
which
scored
chatbots
human
experts,
Dynamic
Assessment
(DA)
approach
humor
as
means
for
enhancing
chatbots’
outcomes.
results
are
encapsulated
21
original
and,
sometimes,
surprising
observations.
Journal of Cognitive Psychology,
Год журнала:
2024,
Номер
unknown, С. 1 - 12
Опубликована: Авг. 27, 2024
Recent
advances
in
artificial
intelligence
have
reinvigorated
the
longstanding
debate
regarding
whether
or
not
any
aspects
of
human
cognition—notably,
high-level
creativity—are
beyond
reach
computer
programs.
Is
creativity
entirely
a
computational
process?
Here
I
consider
one
general
argument
for
dissociation
between
and
creativity,
which
hinges
on
role
consciousness—inner
experience—in
cognition.
It
appears
unlikely
that
inner
experience
is
itself
process,
implying
it
cannot
be
instantiated
an
abstract
Turing
machine,
nor
current
architecture.
Psychological
research
strongly
implies
integrates
emotions
with
perception
thoughts.
This
integrative
function
consciousness
likely
plays
key
mechanisms
support
creativity.
conclusion
dovetails
anecdotal
reports
creative
individuals,
who
linked
intrinsic
motivation
to
create,
ability
access
novel
connections
ideas.
This
study
investigates
the
indispensable
role
of
human
skills—such
as
empathy,
ethical
judgment,
and
nuanced
understanding—in
development
application
artificial
intelligence
(AI)
within
higher
education,
highlighting
unique
contributions
neurodivergent
perspectives
in
creating
a
symbiotic
human-AI
relationship.
Drawing
upon
research
that
evidences
superior
performance
diverse
teams
creativity
innovation,
paper
argues
for
integration
neurodiversity
into
AI
means
to
address
philosophy
'fearing
Other,'
thereby
mitigating
biases
fostering
interactions.
The
technology
sector's
adoption
Diversity,
Equity,
Inclusion
(DEI)
programs,
including
biopsychosocial
interventions
environmental
adaptations
support
workforce,
serves
model
education.
By
leveraging
estimated
15-20%
global
population
which
is
neurodivergent,
this
approach
not
only
aims
alleviate
employment
disparities
faced
by
individuals,
but
also
enriches
innovative
capacities
educational
systems.
concise
analysis
advocates
an
landscape
replicates
embodies
values,
thanks
invaluable
community.
Innovation in Language Learning and Teaching,
Год журнала:
2024,
Номер
unknown, С. 1 - 13
Опубликована: Авг. 1, 2024
Artificial
intelligence
(AI)
has
been
considered
a
powerful
tool
for
fostering
language
learning
and
applied
to
various
language-learning
contexts.
Yet,
teachers
might
lack
adequate
knowledge
about
how
integrate
AI
into
classrooms
facilitate
students'
effectively.
To
address
the
issue,
this
paper
reports
on
an
innovative
practice
enhance
secondary
school
creative
writing
by
leveraging
AI's
capability
natural
generation
(NLG).
Specifically,
we
describe
two
designs
teaching
students
write
short
stories
with
AI-NLG
(i.e.
Text
Generator),
one
aiming
at
providing
hands-on
experience
other
offering
scaffolds
compose
stories.
We
present
purposes,
intended
outcomes,
activities,
materials
resources
of
designs.
Besides,
discuss
performance
achievements
four
who
learnt
also
analyzed
creativity
in
ideas
their
examine
effects
Generator.
Finally,
reflect
our
implementation
practice,
outline
pedagogical
lessons
learnt,
provide
suggestions
future
research
using
writing.
anticipate
that
educators
researchers
can
replicate,
evaluate
improve
designs,
better
support
AI.
Abstract
Given
the
widespread
integration
of
Social
AI
like
ChatGPT,
Gemini,
Copilot,
and
MyAI,
in
personal
professional
contexts,
it
is
crucial
to
understand
their
effects
on
information
knowledge
processing,
individual
autonomy.
This
paper
builds
Bråten’s
concept
model
power,
applying
offer
a
new
perspective
interaction
dynamics
between
humans
AI.
By
reviewing
recent
user
studies,
we
examine
whether
how
models
world
reflected
may
disproportionately
impact
human-AI
interactions,
potentially
leading
monopolies
where
impacts
human
beliefs,
behaviour
homogenize
worldviews
its
users.
The
power
provides
framework
for
critically
evaluating
influence
that
has
communication
meaning-making,
thereby
informing
development
future
systems
support
more
balanced
meaningful
interactions.
