The on-wiki version of this newsletter can be found here:
https://www.wikifunctions.org/wiki/Wikifunctions:Status_updates/2025-05-09
----
Abstract Wikipedia and the Wikimedia AI Strategy
Last week, the Wikimedia Foundation’s AI Strategy brief
<https://meta.wikimedia.org/wiki/Strategy/Multigenerational/Artificial%20int…>
was
announced. The diff post announcing
<https://diff.wikimedia.org/2025/04/30/our-new-ai-strategy-puts-wikipedias-h…>
the
brief gives a great summary: our AI strategy is to double down on
supporting the volunteers behind the Wikimedia projects.
How does this fit with Abstract Wikipedia? Is there a place for AI
technology in Abstract Wikipedia?
A quick sidenote: a few years ago, our plans for Abstract Wikipedia would
have been considered use of AI technologies, when topics such as Knowledge
Representation and Natural Language Generation were considered sub-fields
of AI. But we recognize that times and languages change, and that today the
term AI is almost exclusively used to refer to large language models and
other machine-learned models. For this text, we accept this terminology.
<https://www.wikifunctions.org/wiki/File:Abstract_wikipedia_mockup.png>Mockup
of Abstract Wikipedia from 2021
Right from the start in the paper introducing Abstract Wikipedia
<https://cacm.acm.org/opinion/building-a-multilingual-wikipedia/> in 2020,
we sketched out a three-panel UX mock-up about how the editing workflow
could work (compare to the mock-up on the right):
1. The panel on the left is a text box, allowing contributors to write
and edit text in their language freely.
2. The panel in the middle shows an interpretation of the text being
entered in the left panel. This is a Wikifunctions object, and the
contributor can edit the object directly, in order to fix errors or refine
the content. It updates automatically when the text in the left panel is
being modified.
3. The panel on the right shows the text that results from rendering the
object in the middle panel. It updates automatically as the middle panel is
being modified. It shows the result in a number of languages as selected by
the contributor.
To the right is a new mock-up, based on the current interface designs. The
idea remains the same.
<https://www.wikifunctions.org/wiki/File:Abstract_Wikipedia_Mockup_2025.png>Mockup
of Abstract Wikipedia based on the current interface
The step from the middle panel to the right panel is what we are currently
working on with Wikifunctions: helping our community write functions that
generate natural language text based on abstract content objects. But how
do we get from the free text in the left panel to the object in the middle
panel?
That’s where we expect language models will come in. A language model would
translate the text in the left panel to the abstract representation for the
middle panel, prompting the human using the tool to consider if the
generated output is what they expect. In 2020, we were merely hopeful that
this would work; five years later, the incredible progress in language
models are giving us great confidence that this will work, and thus allow
us for a feasible UX for Abstract Wikipedia.
Such a usage of AI is exactly aligned with the AI strategy of supporting
contributors, by making it easier, faster, and simpler for them to
contribute to Abstract Wikipedia. Contributors will not need to learn and
remember the constructors we have, or understand how they fit together: the
AI will propose that conversion. At the same time, the right panel will
allow for an immediate check whether the AI got it right. In the cases it
didn’t, the contributor can choose to tweak their input, directly modify
the object, or choose one of the alternative interpretations the AI came up
with. By seeing the feedback in the form of results in several languages,
we can reduce issues with ambiguity and increase confidence that the
abstract representation is indeed what a human wanted. This is an
iterative, human-in-the-loop approach in which the contributor verifies the
content before publishing, making sure to centre the human factor — the
many people in our communities who are the key to Wikimedia's success.
The Wikimedia AI strategy also calls for a nuanced approach to
multi-lingual support. Here, Abstract Wikipedia has a unique advantage:
using Wikifunctions, we can automatically create abstract content and text
generated from it, in all languages we have functions and lexemes for! This
approach would allow us to train an LLM specifically for Abstract Wikipedia
as far as the generation functions support the given language. We hope to
get usable interpretations even for languages the foundational model has
not been trained on – especially given the human-in-the-loop approach of
the user experience.
Thanks to Leila Zia and Chris Albon for their amazing work on the AI
strategy brief!
Recent Changes in the software
Our first new embedded-call editing feature lands this week: We now show a
"preview" of the result in the dialog as you create or adjust your Function
call (T391336 <https://phabricator.wikimedia.org/T391336>). We hope that
this helps people use the tool more fluidly.
We've also now added some information to Special:Statistics
<https://www.wikifunctions.org/wiki/Special:Statistics> about the number of
Functions, Types, Implementations, Test cases, and overall Objects on the
wiki, and also provided these as wikitext magic words, which can be used on
the Main Page (T345477 <https://phabricator.wikimedia.org/T345477>).
We adjusted the handler for cross-wiki Function calls to handle invalid
JSON input more gracefully, such as when a user tries to call the URL with
manually-given (poorly-encoded) input. We extended the visual diffing code
we registered with the visual editor to work better, and not leave behind
debugging comments.
Our test code was adjusted by User:Umherirrender
<https://www.wikifunctions.org/wiki/User:Umherirrender> to be
forwards-compatible with PHPUnit 10 by converting our data provider to be
static (T332865 <https://phabricator.wikimedia.org/T332865>). We refactored
some of our code around errors, dropping a now-unused parameter, and
simplified a potential infinite recursion in the test stack by always
registering the Z504/Object not found error, so when an Object is not found
we only get one level of errors.
As a measure to unbreak the system when a test case triggers an error, we
now (at least, temporarily) no longer pass a resultant error into the
test-checker, but instead the return value, which will be void (T393156
<https://phabricator.wikimedia.org/T393156>). The system was intended to
allow test cases to be written that check that the correct error is
returned when bad user input happens (e.g. a user tries to divide by zero,
or gets the seventh result from a list of six items), but in practice the
error response would sometimes be so large that it would cause the system
to choke. In future, we'll consider different ways that we might want to
test errors in such cases.
Hackathon 2025 in Istanbul
Members of the Abstract Wikipedia team attended the Wikimedia Hackathon 2025
<https://www.mediawiki.org/wiki/Wikimedia%20Hackathon%202025> in Istanbul.
<https://www.wikifunctions.org/wiki/File:Team_Photo_Abstract_Wikipedia_Hacka…>Team
photo of the Abstract Wikipedia team at the Hackathon 2025 in Istanbul
It was great to speak with many people who are curious, excited, intrigued
about Wikifunctions and Abstract Wikipedia — and some who are concerned. We
hope we answered your queries and sparked further ideas about what will
come next. Certainly, we found it hugely valuable to discuss issues like
how well natural language generation might scale across the huge range of
different languages and content types, possible future uses like rich text
or even video output, and the future of citations at Wikimedia and how
Abstract Wikipedia might be able to use them most powerfully. We're
grateful for everyone's time, and look forward to the next event where we
might meet more community members, at Wikimania 2025
<https://wikimania.wikimedia.org/wiki/2025:Wikimania> in Nairobi.
Virtual community meetings
No recording of this Monday's Volunteers’ Corner has been made, because we
decided with the volunteers to have more private conversations and not
record.
We are planning the next NLG SIG meeting for May 20, if we get proposed
topics for the agenda. Please add your topics here
<https://www.wikifunctions.org/wiki/Wikifunctions:NLG_SIG>. Otherwise we
will cancel the meeting.
Knowledge Graph Insights podcast
Larry Swanson interviewed Denny for Episode 32 of his podcast Knowledge
Graph Insights, talking about Wikifunctions, Abstract Wikipedia, and
Wikidata. You can listen to the episode from the podcast's website
<https://knowledgegraphinsights.com/denny-vrandecic/>, or wherever you
listen to podcasts.
Fresh Functions weekly: 38 new Functions
This week we had 38 new functions. Here is a list of functions with
implementations and passing tests to get a taste of what functions have
been created. This week, a lot of arithmetic functions in the mix! Thanks
everybody for contributing.
- is not empty string (Z24331)
<https://www.wikifunctions.org/wiki/Z24331>
- squared norm of a vector (rational) (Z24342)
<https://www.wikifunctions.org/wiki/Z24342>
- norm of a vector (Z24346) <https://www.wikifunctions.org/wiki/Z24346>
- Lorentz factor from velocity as vector (Z24350)
<https://www.wikifunctions.org/wiki/Z24350>
- partial sum of power series (Z24372)
<https://www.wikifunctions.org/wiki/Z24372>
- partial sum of zero-centred power series (Z24374)
<https://www.wikifunctions.org/wiki/Z24374>
- generate list of powers of q from 0 to n (Z24382)
<https://www.wikifunctions.org/wiki/Z24382>
- generate list of [f(0) to f(n)] (Z24387)
<https://www.wikifunctions.org/wiki/Z24387>
- partial sum of power series from a_n = 1/f(n) (Z24395)
<https://www.wikifunctions.org/wiki/Z24395>
- is rational in range (inclusive) (Z24403)
<https://www.wikifunctions.org/wiki/Z24403>
- multiply rational and matrix (Z24436)
<https://www.wikifunctions.org/wiki/Z24436>
- order lexeme forms by features and languages (Z24450)
<https://www.wikifunctions.org/wiki/Z24450>
- get general Grapheme_Cluster_Break from codepoint (Z24459)
<https://www.wikifunctions.org/wiki/Z24459>
- get Nth code point of String (Z24472)
<https://www.wikifunctions.org/wiki/Z24472>
- lexeme form representations (first in ranked form) (Z24483)
<https://www.wikifunctions.org/wiki/Z24483>
- square of rational number (Z24487)
<https://www.wikifunctions.org/wiki/Z24487>
- Clebsch-Gordan coefficient (squared and signed) (Z24497)
<https://www.wikifunctions.org/wiki/Z24497>
- square root of rational with precision (Z24505)
<https://www.wikifunctions.org/wiki/Z24505>
- same rational within tolerance (Z24506)
<https://www.wikifunctions.org/wiki/Z24506>
- 10^n (natural number) (Z24517)
<https://www.wikifunctions.org/wiki/Z24517>
- 10^n (integer to rational) (Z24525)
<https://www.wikifunctions.org/wiki/Z24525>
- Newton's method estimate within tolerance (Z24539)
<https://www.wikifunctions.org/wiki/Z24539>
A complete list of all functions sorted by when they were created
<https://www.wikifunctions.org/wiki/Special:ListObjectsByType?type=Z8&orderb…>
is
available.
