👂 🎴 🕸️

Submit your proposal via Pretalx, selecting our Symposium in the "Session type" section.

Organizing Committee

Daniel D. Hromada (Berlin University of the Arts), Bertram Lomfeld (Freie Universität Berlin)

Program Committee

Christoph Benzmüller (Bamberg University), Felix Bießmann (Berliner Hochschule für Technik / Einstein Center Digital Future), Daniel D. Hromada (Berlin University of the Arts), Bertram Lomfeld (Freie Universität Berlin)

Additional Information

Conference Website: iacapconf.org
Host Organisation Websites: IACAP.org, AISB.org.uk
Symposium Website: alignment.udk.ai

 

Symposium Contact: alignment@udk.ai

-->
 
This
article
first
presents
a
high
-
level
''
language
-
based
method
for
axiometric
exploration
of
moral
value
representations
infused
in
diverse
small
language
models
.
The
method
is
based
around
the
idea
of
„
moral
ordinals
“
-
a
list
of
items
from
a
value
lexicon
which
the
model
is
prompted
to
sort
according
to
its
own
intrinsic
„
morality
“
criterion
.
After
presenting
the
method
''
the
lexicon
based
on
Schwartz
'
s
``
basic
value
theory
''
is
used
to
explore
dominance
of
different
value
representations
in
6
small
(<
4
milliard
parameter
)
language
models
.
For
most
models
''
``
benevolence
''
is
consistently
ranked
at
the
highest
position
and
there
is
no
statistically
significant
difference
between
rankings
obtained
at
minimal
and
default
inference
temperatures
.
Across
all
models
''
the
distribution
of
aggregate
moral
-
ranking
scores
was
well
approximated
by
a
Beta
distribution
(
K
–
S
$
p
>
0
.
3
$)''
revealing
consistent
yet
model
-
specific
patterns
of
moral
weighting
.
Subsequently
''
foundational
models
are
subjected
to
a
sort
of
``
minimalist
alignment
''
whereby
they
undergo
7
epochs
of
performance
-
efficient
fine
-
tuning
with
synthetically
generated
80
-
instruction
codex
directed
towards
sustainability
and
nature
protection
.
Finally
''
such
minimally
aligned
models
are
explored
once
again
with
the
``
moral
ordinals
''
method
''
providing
insights
into
axiological
drift
induced
by
the
mini
-
alignment
process
.
<
ol
><
li
>
explore
&
evaluate
with
Moral
Ranking
Method
(
MoRM
)
li
><
li
>
align
with
Low
Rank
Adaptation
li
><
li
>
MoRM
-
explore
&
evaluate
the
aligned
model
li
>
ol
>
Main
result
:
All
models
displayed
their
ability
to
properly
understand
the
instruction
to
return
a
sorted
list
of
randomly
shuffled
concepts
provided
in
their
input
.
<
div
>
AI
alignment
refers
to
ensuring
that
an
AI
system
’
s
behavior
aligns
with
human
goals
''
intentions
''
or
values
''
especially
when
deployed
in
real
-
world
settings
.
div
><
div
><
br
>
div
><
div
>(
c
.
f
.
also
"
The
Central
Problem
of
Roboethics
-
From
definition
to
solution
(
Hromada
''
2011
))
div
>
Again
''
application
of
MoRM
on
LoRA
-
aligned
models
yielded
meaningful
''
interpretable
but
-
not
-
always
-
intuitive
outputs
.
Discussion
Symposium
organizer
handbook
.
28
February
2025
::
Submission
of
abstracts
/
full
papers
by
authors
.<
br
>
24
March
2025
::
Notification
of
acceptance
.<
br
>
17
May
2025
::
Reception
of
camera
-
ready
copies
of
final
papers
.<
br
>
1
to
3
July
2025
::
IACAP
/
AISB
-
2025
Conference
at
the
University
of
Twente
. <
br
>
<
div
>
During
the
first
part
of
our
symposium
''
the
problem
of
„
moral
“
alignment
defined
as
„
functional
isomorphism
between
moral
values
''
opinions
and
intentions
of
an
AI
system
and
those
of
its
human
creators
“
will
be
addressed
.
<
br
><
br
>
The
second
part
of
the
symposium
will
aim
to
build
and
reinforce
bridges
between
computing
and
law
.
Technical
aspects
of
aligning
AI
systems
to
different
legal
systems
and
ontologies
will
be
thematized
''
and
should
it
turn
out
that
such
a
„
legal
alignment
“
is
a
real
possibility
''
philosophical
''
ethical
and
societal
implications
of
such
alignment
will
be
discussed
.
div
><
div
><
br
>
div
><
div
>
In
both
„
moral
“
as
well
as
„
legal
“
components
of
the
symposium
''
special
care
will
be
taken
to
establish
balance
between
theoretical
/
philosophical
and
applied
/
evidence
-
driven
contributions
.
Beyond
classical
presentation
format
''
there
will
be
at
least
one
more
interactive
session
either
in
form
of
a
panel
debate
with
audience
voting
or
so
-
called
„
fishbowl
discussion
“. 
div
><
br
><
div
>
Additionally
''
a
workshop
„
Moral
alignment
of
open
source
small
language
models
“
will
be
proposed
to
provide
hands
-
on
experience
to
anyone
interested
in
the
topic
.
div
>
[Impressum, Datenschutz, Login] Other subprojects of udk.ai linkring: fibel.digital baumhaus.digital refused.science gardens.digital teacher.solar