Like if this is a crowdsourcing project, why not do a first pass with an LLM and present users with both the image and the best-effort LLM pass?
Later
I signed up, went to the current missions, and they all seem to post post-1900 and all typeset. They're blurry, but 4o cuts through them like a hot knife through butter.
I expect thats a common theme from companies like that, yet I don't think they understand the issue they think they have there.
Why not have the LLMs do as much work as possible and have humans review and put their own name on it? Do you think they need to just trust and publish the output of the LLM wholeheartedly?
I think too many people saw what a few idiot lawyers did last year and closed the book on LLM usage.
I’m trying to do this for old Latin books at the Embassy of the Free Mind in Amsterdam. So many of the books have never been digitized, let alone OCRd or translated. There is a huge amount of work to be done to make these works accessible.
LLMs won’t make it perfect. But isn’t perfect the enemy of the good? If we make it an ongoing project where the source image material is easily accessible (unlike in a normal published translation, where you just have to trust the translator), then the knowledge and understanding can improve over time.
This approach also has the benefit of training readers not to believe everything they read — but to question it and try to get directly at the source. I think that’s a beautiful outcome.
No, the alternative is volunteers transcribing. Like this project.
Not every problem needs a computer.
That's not a good way to improve on the accuracy of the LLM. Humans reviewing work that is 95% accurate are mostly just going to rubber-stamp whatever you show them. This is equally a problem for humans reviewing the work of other humans.
What you actually want, if you're worried about accuracy, is to do the same work multiple times independently and then compare results.
Edit: apparently it’s called cross writing [1]
Then you have the problem that some of these ancestors not only had terrible penmanship but also spelled multi-syllabic words phonetically since they likely were barely educated kids who spent more time when they were young working on the farm or ranch instead of attending school where they would've learned how to spell correctly.
I don't know whether your LLM can handle English words spelled phonetically written in cursive by an individual who had no consistency in forming letters in the words. It is clear after reading a lot of correspondence from this person that they ignored things that didn't seem important in the moment like dotting i's or crossing t's or forming tails on g's, p's, j's, or even beginning letters consistently since they switched between cursive and block letters within a sentence, maybe while they paused to clarify their thoughts. I don't know but it is fascinating to take a walk through life with someone you'll never meet and to discover that many of the things that seemed awesome to you as a kid were also awesome to them and that their life had so many challenges that our generations will never need to endure.
Some of my people have the most beautiful flowing cursive handwriting that looks like the cursive that I was taught in grade school. Others have the most beautiful flowing cursive with custom flourishes and adornments that make their handwriting instantly recognizable and easy to read once you understand their style.
I think there are plenty of edge cases where LLMs will take a drunkard's walk through the scribble and spit out gibberish.
I'm reminded of an old joke though.
Ronald Reagan woke up one snowy Washington, DC morning and took a look out of the window to admire the new-fallen snow. He enjoys the beautiful scene laid out before him until he sees tracks in the snow below his window and a message obviously written in piss that said - "Reagan sucks".
He dispatched the Secret Service to the site where samples were taken of the affected snow and photos of the tracks of two people were made.
After an investigation he receives a call from the Secret Service agent in charge who tells him he has some good news and some bad news for him.
The good news is that they know who pissed the message. It was George HW Bush, his Vice President. The bad news is that it was Nancy's handwriting.
[0] https://catalog.archives.gov/id/54921817?objectPage=8&object...
[1] Reproducing here since I cannot share the chat since it has user uploaded images. " The text in the top half of the image is handwritten and partially difficult to read due to its cursive style and some smudging. Here's my best transcription attempt for the top section:
...resident within four? years, swears and says that the name of the John Hopper mentioned in the foregoing declaration is the same person, and he verily believes the facts as stated in the declaration are true.
He further swears that the said John Hopper is in reduced and indigent circumstances and requires the aid of his country.
The declarant further swears he has no evidence now in his power of service, except the statement of Capt. (illegible name), as to his reduced circumstances ...
Sworn to before me, this day...
Some parts remain unclear due to the handwriting, but let me know if you'd like me to attempt further clarification on specific sections!"
> In fact it seems to mix up some portions of the latter half of the typed text with the written text in the portion of it's "transcription" about "reduced and indigent circumstances".
What typed form? What typed text? That image is a single handwritten page, and the writing is quite clean, not "barely legible".† The file related to John Hopper appears to be 59 pages, and some of them are typed, but they're all separate images.
Are you trying to process all 59 pages at once? Why?
I should note that transcription is an excellent use of an LLM in the sense of a language model, as opposed to an "LLM" in the sense of several different pieces of software hooked together in cryptic ways. It would be a lot more useful, for this task, to have direct access to the language model backing 4o than to have access to a chatbot prompt that intermediates between you and the model.
† My biggest problems in reading the page: Cursive n and u are often identical glyphs (both written и), leading me to read "Ind." as "Jud."; and I had trouble with the "roster" at the bottom of the page. What felt weirdest about that was that the crossbar of the "t" is positioned well above the top of the stem, but that can't actually be what tripped me up, because on further review it's a common feature of the author's handwriting that I didn't even notice until I got to the very end of the letter. It's even true in the earlier instance of "Roster" higher up on the page. So my best guess is that the "os" doesn't look right to me.
I misread 1758 as 1958, too, but hopefully (a) that kind of thing wears off as you get used to reading documents about the Revolutionary War; and (b) it's a red flag when someone who died in 1838 was born in 1958 according to a letter written in 1935.
Did the link in my comment not take you to a single page (I just tested it in incognito mode too..)? For me it's this image [0] and no I tried just this one page and it didn't do well. If you can get it to work let me know the prompt it was late for me and it
[0] https://s3.amazonaws.com/NARAprodstorage/opastorage/live/17/...
(page 8 of "Revolutionary War Pension and Bounty Land Warrant Application File W. 7785, John Hopper, N.C.")
I agree that your description of the image the link shows you, which appears to be page 52 of the same file, makes sense. I can read ... some of the handwritten words. None of the long ones.
Anyways yes that handwritten text is an example where LLMs just cant hack it and people seem to be able to. There's a pretty thorough transcript of the upper handwritten portion of the page I was referencing available from a user. It's a great example of why you can't just throw an LLM at problems like this. At best they're a tool people can use to transcribe loads of them quickly but it still needs to be hand checked for accuracy, completeness, and relevance.
Possibly for the reason that came up in your other post: you mentioned that you spot checked the result.
Back when I was in historical research, and occasionally involved in transcription projects, the standard was 2-3 independent transcriptions per document.
Maybe the National Archive will pass documents to an LLM and use the output as 1 of their 2-3 transcriptions. It could reduce how many duplicate transcriptions are done by humans. But I'll be surprised if they jump to accepting spot checked LLM output anytime soon.
I think people may be kidding themselves a little bit about this stuff.
But every time I find something that I think "This one is surely easy enough!" it's usually wrong. US revolutionary war cursive is on the easy end; it's quite similar to modern cursive, and what is of training data in the datasets is probably a lot like it, if not actually in it - historians who test this complain about overfitting. Which I believe, because as I said, I see that it's bad at generalizing.
I'm confused by what you're asking. Are you asking me to like (upvote) your comment if this is a crowdsourcing project? Don't we already know it is a crowdsourcing project?
“So if this is a crowdsourcing project…”
Like is serving as an indication that someone else approximately said the phrase it introduced, in a way often associated with the “Valley Girl” social dialect but regularly seen outside of it.
https://en.wikipedia.org/wiki/Like#As_a_colloquial_quotative
Correct, but that's not a quotative use of the word. It's a discourse particle. You want to link one subsection down, like as a discourse particle.
https://en.wikipedia.org/wiki/Like#As_a_discourse_particle,_...
It was more successful at a few others I tried but it's still a task that requires manual processing like a lot of LLM output to check for accuracy and prompt modification to get it to output what you need for some documents.
https://catalog.archives.gov/id/54921817?objectPage=8&object...
“Some participants have dedicated years of their lives to the program—like Alex Smith, a retiree from Pennsylvania. Over nine years, he transcribed more than 100,000 documents”
Have different LLMs transcribe those same documents and compare to see if the human or machine is or accurate and by how much.
https://trustdecision.com/resources/blog/revolutionizing-ocr...
Insisting we switch to that definition is just being unproductive and unhelpful. And it's pure semantics because you know what they meant.
“Our internal tests reveal a leap in accuracy from 98.97% to 99.56%, while customer test sets have shown an increase from 95.61% to 98.02%. In some cases where the document photos are unclear or poorly formatted, the accuracy could be improved by over 20% to 30%.”
(I always go over the transcript by hand, but I'd have to do that with OCR anyway).
As an example look at subtitle rips for DVD and Blu-ray. The discs store them as images of rendered computer text. A popular format for rippers is SRT, where it will be stored as utf-8 and rendered by the player. So when you rip subtitles, there's an OCR step.
These are computer rendered text in a small handful of fonts. And decent OCR still chokes on it often.
If 100% is your standard, good luck solving anything ever.
Not necessarily, I'd be surprised if I could fully understand my old handwritten notes from when I was in school (years ago), since I've always had messy handwriting and no longer have the context in each subject matter to guess.
LLMs could help in some of those cases, since it would have knowledge of history/chemistry/etc. and could fill in the blanks better than I could at this point. Though the hallucinations would no doubt outweigh it.
https://trustdecision.com/resources/blog/revolutionizing-ocr...
> Our internal tests reveal a leap in accuracy from 98.97% to 99.56%, while customer test sets have shown an increase from 95.61% to 98.02%. In some cases where the document photos are unclear or poorly formatted, the accuracy could be improved by over 20% to 30%.
While a small percentage increase, when applied to massive amounts of text it’s a big deal.
Even if LLMs can push a 99.9% accuracy to 99.99, at least an OCR-based system can be audited. Ask an OCR vendor why the machine confused "Vancouver WA" and "Vancouver CA" and one can get a solid answer based in repeated testing. Ask an LLM vendor why and, at best, you'll get a shrug and some line citing how much better they were in all the other situations.
Looking at the (admittedly single) example from the National Archives seems a bit more open than perhaps the other two examples. It’s not impossible thst LLMs could help with this
> The agency uses artificial intelligence and a technology known as optical character recognition to extract text from historical documents. But these methods don’t always work, and they aren’t always accurate.
The document at the top is likely an especially easy document to read precisely because it's meant to be the hook to get people to sign up and get started. It isn't going to be representative of the full breadth of documents that the National Archives want people to go through.