[HN Gopher] Citation Needed - Wikimedia Foundation's Experimenta...
       ___________________________________________________________________
        
       Citation Needed - Wikimedia Foundation's Experimental LLM/RAG
       Chrome Extension
        
       Author : brokensegue
       Score  : 143 points
       Date   : 2024-05-11 21:12 UTC (1 days ago)
        
 (HTM) web link (chromewebstore.google.com)
 (TXT) w3m dump (chromewebstore.google.com)
        
       | brokensegue wrote:
       | Experimental LLM powered RAG application for checking claims on
       | the Internet against Wikipedia.
       | 
       | You can read more about it at
       | https://meta.wikimedia.org/wiki/Future_Audiences/Experiment:...
       | 
       | Disclaimer: I worked on this.
        
         | NegativeLatency wrote:
         | Any plans for a Safari extension?
        
           | andybak wrote:
           | Or Firefox
        
         | purple-leafy wrote:
         | Hey matey, do you folks need any more devs to bring ideas or
         | code?
         | 
         | I'm heavily into browser extension development! I've done some
         | insane things with them.
         | 
         | I've built about 8 browser extensions in the last 6 months,
         | most of them have thousands of users and one of them had half a
         | million users
         | 
         | Currently building an LLM powered design assistant extension.
         | 
         | If you'd like to chat im reachable by email at
         | "hello[at]papillonsoftware[dot]dev"
        
           | squigz wrote:
           | > I've built about 8 browser extensions in the last 6 months,
           | most of them have thousands of users and one of them had half
           | a million users
           | 
           | Do you have any concerns about your ability to properly
           | maintain so many extensions?
        
             | purple-leafy wrote:
             | Not really, most of them are "feature complete" as they
             | target a very small surface area or feature.
             | 
             | For instance, one of them reveals salaries on job seeker
             | sites, and is feature complete as it does what it's meant
             | to do bug free and fast
        
               | squigz wrote:
               | No web extension is going to remain feature complete or
               | bug free for very long. What happens when the job seeker
               | sites change their HTML/CSS/JS?
        
         | card_zero wrote:
         | It looks like this doesn't check whether the article itself
         | cites a source for the claim. Is that why it's called "Citation
         | Needed"? Because it doesn't actually cite anything?
        
         | bitsinthesky wrote:
         | Anywhere that gets into technical details and design?
        
           | input_sh wrote:
           | Not the person you've responded to, but I found this:
           | https://gitlab.wikimedia.org/repos/future-
           | audiences/citation...
        
       | aurareturn wrote:
       | This is a great idea. Hopefully we also have LLMs fact checking
       | and flagging Wikipedia articles.
        
         | ysavir wrote:
         | Wouldn't that just be checking wikipedia articles against the
         | same wikipedia articles which the LLM originally trained on?
        
           | relyks wrote:
           | No, citations are supposed to be from reliable secondary
           | sources or authoritative primary ones external to Wikipedia
        
             | josefx wrote:
             | Many of those sources are not available online (books),
             | point at paywals (research papers) or are dead . Unless you
             | have an API that can bypass these issues reliable you are
             | stuck with a tool that has already landed several lawyers
             | in hot water for making up citations on the fly.
        
               | falcor84 wrote:
               | The Wikipedia Library project [0] grants active editors
               | access to a wide range of otherwise paywalled sources. I
               | wonder if it could not be extended to this sort of bot.
               | 
               | [0] https://diff.wikimedia.org/2022/01/19/the-wikipedia-
               | library-...
        
             | ysavir wrote:
             | What LLM will we check those against? How do we trust that
             | its source materials are accurate and correct?
        
               | shiomiru wrote:
               | I think the idea is that you feed the LLM the article &
               | the source material (from citations) and it checks if
               | they match up.
        
               | ysavir wrote:
               | Sure, but what happens when the article is updated at a
               | later date, or rescinded, etc.? Should the LLMs be
               | trained to repeat the article verbatim, or to say
               | "according to this article[0], blah blah blah" with links
               | to the sources?
               | 
               | Wikipedia works because we can update it in real time in
               | response to changes. LLMs that need to constantly recrawl
               | every time a page on the internet is updated, and that
               | properly contextualize the content of that page, is a
               | huge ask. Because at that point, it stops being an LLM
               | and starts being a very energy-hungry search engine.
        
               | shiomiru wrote:
               | Well, it's just a bot, so no need for it to instantly
               | react to any and every update.
               | 
               | I also have my doubts on whether it is possible to
               | implement efficiently (or at all). I suspect that just
               | yanking in the article and all the sources is non-
               | feasible, and any smaller chunking would be missing too
               | much context. Plus LLM logical capabilities are
               | questionable too, so I don't know how well the comparison
               | would work...
        
       | visarga wrote:
       | Couple this with a search based article generator so you have an
       | article generator and an article checker, and then off you go to
       | generating 1 trillion pages. Could be useful training content for
       | LLMs but also used by people.
        
       | bawolff wrote:
       | I wonder how this will go over politically with the wikipedia
       | community. AI is such a hot button issue, and the risk of
       | hallucinating and saying something wrong seems more pressing in
       | this application then most.
        
         | jszymborski wrote:
         | I haven't used this, but reading the description, it sounds
         | like it's primarily a search engine for wiki articles related
         | to selected text. If so, I imagine it wouldn't be super
         | susceptible to hallucinations.
        
           | Kwpolska wrote:
           | It uses AI to parse the selected text to choose search
           | keywords, and to parse the related Wikipedia article to
           | decide if it agrees with the selected text. It obviously can
           | bullshit in both cases.
        
             | falcor84 wrote:
             | Searching for keywords shouldn't be likely to hallucinate.
             | And I would assume they would have a subsequent step to run
             | a quick check to see they're really in the text. And if
             | there is some issue, I suppose we can always fall back to
             | something like TF-IDF.
             | 
             | The second part does seem more problematic, but still, as
             | essentially a yes/no question, it should be significantly
             | less likely to hallucinate/confabulate than for other
             | tasks.
        
               | Kwpolska wrote:
               | The extension appears to also produce an explanation of
               | its decision, so there is potential to bullshit: https://
               | meta.wikimedia.org/wiki/Future_Audiences/Experiment:...
               | 
               | Also, if you look into their "wrong" example closer, it
               | is a bit misleading, as both sources are correct. Joe
               | Biden was 29 on election day, but 30 when he was sworn
               | in. Understanding this requires more context than the LLM
               | was apparently provided.
        
             | AJRF wrote:
             | Honest question - do you expect there to be hallucinations
             | in this case? I have extensive experience in LLMs and also
             | from talking to peers with similar experience, it is
             | uncontroversial to say that given grounding like this LLMs
             | won't hallucinate.
             | 
             | I am not sure if when people say this they just don't have
             | experience building with LLMs or they do and have
             | experience that would make for a very popular and
             | interesting research paper.
        
               | Kwpolska wrote:
               | The burden of the proof of no bullshit is on the LLM
               | proponents.
        
               | hombre_fatal wrote:
               | Well wait a sec, you'd be just as guilty of confident
               | bullshit if your claims above don't pan out, and they
               | didn't even come from an LLM so it's worse.
        
               | simonw wrote:
               | "it is uncontroversial to say that given grounding like
               | this LLMs won't hallucinate"
               | 
               | I disagree. LLMs that have been "grounded" in text that
               | has been injected into their context (RAG style) can
               | absolutely stoln hallucinate.
               | 
               | They are less likely to, but that's not the same as
               | saying they "won't hallucinate" at all.
               | 
               | I've spotted this myself. It's not uncommon for example
               | for Google Gemini to include a citation link which, when
               | followed, doesn't support the "facts" it reported.
               | 
               | Furthermore, if you think about how most RAG
               | implementations work you'll spot plenty of potential for
               | hallucination. What if the text that was pulled into the
               | context was part of a longer paragraph that started "The
               | following is a common misconception:" - but that prefix
               | was omitted from the extract?
        
       | qrian wrote:
       | Asking about itself returns this:
       | 
       | > "Citation Needed is an experimental feature developed in 2024"
       | 
       | - The provided passages do not contain any information about a
       | feature called 'Citation Needed' being developed in 2024.
       | 
       | - Wikipedia
       | 
       | - Discouragement in education
       | 
       | - not be relied
       | 
       | I know I'm not using it for intended purposes but it seemed
       | funny.
        
       | mattyyeung wrote:
       | Can quotations be hallucinated? Or are you using something like
       | "deterministic quoting"[1]?
       | 
       | Disclosure: author on that work.
       | 
       | [1] https://mattyyeung.github.io/deterministic-quoting
        
       | tuananh wrote:
       | No firefox extension though.
        
         | neilv wrote:
         | If Wikimedia Foundation didn't get paid for basing this project
         | on an aggressively embrace&extend browser, they should look
         | into whether they're leaving money on the table, since projects
         | like this help extinguish the browser's competition.
        
       | youssefabdelm wrote:
       | Does this only work on Chrome? Can't seem to make it work on Arc.
        
       | Daub wrote:
       | > A chrome extension for finding citations in Wikipedia
       | 
       | In academia, Wikepedia citations are generally a no no. One
       | reason is their unrelaibity (the author is citing a source that
       | they themselves can edit). More importantly, Wikepedia may be a
       | good place to find primary sources, but in itself it is a
       | secondary source.
        
         | jimbobthrowawy wrote:
         | It really shouldn't, considering they have a rule about not
         | using primary sources.
        
           | _notreallyme_ wrote:
           | Yes, they explicitly classify wikipedia as a tertiary source
           | [1].
           | 
           | Wikipedia is good for finding secondary source, and then
           | primary sources by following the links.
           | 
           | [1] https://en.wikipedia.org/wiki/Wikipedia:Primary_Secondary
           | _an...
        
         | boxed wrote:
         | That justification seems a bit behind the times honestly. We've
         | now seen actual academic fraud on a massive scale with
         | extremely little in the way of a correction to fix this, while
         | at the same time we've seen Wikipedia handle abuse extremely
         | well. The academic fraud is a threat to Wikipedia, more than
         | using wikipedia links is a threat to academia.
        
         | Waterluvian wrote:
         | This seems no different than it's always been. Even before
         | Wikipedia you would not cite secondary sources. But you sure
         | would use them to get a foothold on a topic and find some of
         | those sources.
        
         | lozenge wrote:
         | The point is to find the information in Wikipedia which often
         | then has a citation to another source. If you search Google you
         | often find repetitions of the information but most sites don't
         | cite sources.
        
         | bawolff wrote:
         | > One reason is their unrelaibity (the author is citing a
         | source that they themselves can edit)
         | 
         | There is plenty of reasons why wikipedia is an inapropriate
         | source to cite most of the time in academia, but that surely is
         | not one of them.
         | 
         | Acedemics cite their own papers or other sources they have
         | editorial control over all the time.
        
       | ruined wrote:
       | wikimedia's git repo for this extension
       | 
       | https://gitlab.wikimedia.org/repos/future-audiences/citation...
       | 
       | edit: the readme build instructions are incomplete and i don't
       | think hotreload works. use `npm run build-dev` to get a working
       | build.
       | 
       | it's not obvious to me what prevents this from being a firefox
       | extension as well - it might be the sidebar/sidepanel api
       | differences, but i haven't played with those much
        
       | ale42 wrote:
       | @wikimedia: Firefox version please
        
       ___________________________________________________________________
       (page generated 2024-05-12 23:02 UTC)