Detecting LLM-Generated Texts with “Classical” Machine Learning

cyanydeez

today, sure. Tomorrow, the LLMs will be training the humans thought patterns that will directly start skewing their natural writing. Generation alpha is going to have a lot of trouble if we keep perpetuating the myth that you can really interpret text in an ongoing fashion.

unfocso

I had done the same for classifying and generating bookmarks of thousands of datasheets, along with a very naive yolo-based classificator (to detect pages made out of diagrams and pictures mostly). Done with GLM-OCR, I had to watch text sloooowly crawl out of the llm and still have to live with hallucinations and the model not following the schema

Krssst

The classifier does not seem so big, I wonder if something like it for English could be used in a browser extension to run against every single paragraph being displayed ? If the internet is going to drown in LLM text it would be nice to have tools to detect that automatically just like we have adblockers today to avoid wasting time on ads. (the article was a good read, thanks!)

aberoham

I wonder about this technique vs simple SVM classifiers: https://x.com/rosmine/status/2056406399471558872?s=20

akersten

Text is simply not information dense enough to be able to decode some arbitrary signal of provenance from it. Sure you might be able to detect today's tells (particular sentence structures preferred by Claude, phrases, etc) to get you some arbitrary chance percentage it was machine generated, but it's a bad fiction to perpetuate that any of this is anything more than tarot card reading. Images, absolutely, there are tell-tale artifacts from today's generators that simply aren't emitted by "natural" paths to create them, and you can "detect AI" with high confidence (for now). Words, no, the signal is far too sparse and we are well into undetectable sophistication with today's models, let alone tomorrow's.

XiphiasX

Anything too “clever” and “snappy” = instaLLM

teeray

The problems are simply too great if an LLM detector has any false positives at all. Imagine how soul-crushing writing an entire dissertation by hand and having it rejected because some “good enough” LLM detector decides you write too much like an AI.

gleenn

I think the fundamental problem is that training current SOTA AI models is very expensive. If a simple "classical" model can detect them, presumably at much lower algorithmic cost, then why wouldn't the model trainers use these same tools to feed back into their models to improve them at low cost to make them better? It's an arms race. Any cheap pattern can and presumably will be used to retrain if it becomes and effective way to catch AI.

docheinestages

I think figuring out if a text is AI-made is a losing battle. What could work is gauging how much effort went into writing the text, regardless of who the author might be. What's easy today is generating mountains of text that are extremely hard to read. What requires effort is knowing how to engage the reader, how to keep out extraneous information, and how to keep the text as short as possible without losing details. That needs effort, with or without AI.

metalman

there is not much point in detecting LLM generated text, in that humans are useing info from LLM's, but obfusicting it's origin, with there own garble, along with purely human garble, and almost(but not quite) human LLM product meaning that the threshold for rejecting "data" must be lowered, which personaly means a very very low tollerance for wierdness, except where it can yield imediate possitive cash flow for the rest I do my own research and verification thank you very much

40four

I could be wrong, but I just don’t see how trying to “detect” LLM generated texts is ever going to work. The only thing that makes any sense if you truly want to have confidence a human wrote it is some type of “proof of work“ system. I think there’s a lot of interesting ways to approach the proof of work problem with different pros and cons, but that is where our energy should be focused if we seriously want to solve this problem.

richard_chase

Am I the only who largely enjoys the output of LLMs more than most stuff written by humans? I find myself coming back to old chats with ChatGPT frequently because the output is amazing.

arjie

Neat. I will implement something like this for myself. I just need to reduce the spam a little. Imperfection is okay for a social network context like HN.

connorboyle

> Eventually, I faked my way through the thesis, and life moved on. This is a very startling admission! I checked the Chinese (original?) version of the post, and saw the author uses the word "糊弄" (in the place of "faked"); I'm not a native speaker but I think this may come across more as a self-effacing comment on the low quality and/or effort behind their thesis, whereas the English version implies fraud. May be wise to change this!

woadwarrior01

Small encoder-only transformers are excellent at classifying LLM-Generated Text. I built an on-device iOS app using a custom small encoder that achieves an AUROC of 99.81 on RAID-bench.

throaway54321

I don’t think it actually matters (and it’s a losing strategy as others have noted). This issue with AI generated stuff is that that it’s sometimes asymmetric: either the author worked very little to produce a lot of slop and now the reader(s) all have to do the heavy effort of reading it OR the author puts a little extra work in once and resolves all future readers’ burden. If it was possible to boil down an artifact into a prompt + some resources that would be an interesting tool, or at least some way to tell if some artifact is “worth my time to read”

moxza

The thing I find most encouraging is that the best AI detector is still humans. Don't write the Turing test off yet. From what I understand, your approach is clever, it's like an accent detector. Known models tend toward a specific median approach. Humans have a much richer degree of randomness. Riffing on Anna Karenina... All models are alike in that they present predictable patterns. Humans inevitably write in unique ways. I gave a lot of thought to the idea that humans will devolve to the median led by volume of AI interactions, but in the end, I think we're still interacting with each other when not at work/on machines, and the fact that we even have a genetic heritage is always going to differentiate us.

gdiamos

as soon as you release a way of measuring it, you give LLMs a signal to optimize

maxspero

> Sounds promising, right? I spent some time trying [perplexity], but results were disappointing—plenty of false positives and false negatives, and no reasonable threshold could be set. Perplexity was widely considered SOTA in 2022. One part of it is because everyone was evaluating on open models or closed models that were still close (i.e. GPT-2 vs. GPT-3.5). Today, the gap is so much wider between the models you can use to compute perplexity and the frontier models people actually use. Also so many AI text detection papers used a strawman RoBERTa baseline that was very undertrained for the task. The synthetic mirrors method for data generation used here is the same as what we use at Pangram. Good blog post, thank you for sharing!

sMarsIntruder

Am I wrong or it doesn’t seem to detect the em-dashes as clear warning signal?