Deep learning gets the glory, deep fact checking gets ignored

Post by b0a04gl » Wed, Jun 04, 2025, 3:28 PM UTC

TeMPOraL wrote: post #113

stevenae wrote: post #110

Earlier quoted context omitted.

> Lately, I just steal embeddings from big models and slap a dumb classifier on top. Works better, runs faster, less drama. You may know this but many don't -- this is broadly known as "transfer learning".

Is it, even when applied to trivial classifiers (possibly "classical" ones)? I feel that we're wrong to be focusing so much on the conversational/inference aspect of LLMs. The way I see it, the true "magic" hides in the model itself. It's effectively a computational representation of understanding . I feel there's a lot of unrealized value hidden in the structure of the latent space itself. We need to spend more time…

Post by disgruntledphd2 » Wed, Jun 04, 2025, 3:41 PM UTC

dvfjsdhgfv wrote: post #126

disgruntledphd2 wrote: post #80

Earlier quoted context omitted.

Honestly, if your accuracy/performance metrics are too good, that's almost a sure sign that something has gone wrong. Source: bitter, bitter experience. I once predicted the placebo effect perfectly using a random forest (just got lucky with the train/test split). Although I'd left academia at that point, I often wonder if I'd have dug in deeper if I'd needed a high impact paper to keep my job.

I believe it's very common. At some point I thought about publishing a paper analyzing some studies with good results (published in journals) and showing where the problem with each lies but at some point I just gave up. I thought I will only make the original authors unhappy, everybody else will not care.

Post by tbrownaw » Wed, Jun 04, 2025, 3:52 PM UTC

somenameforme wrote: post #57

tensor wrote: post #55

Earlier quoted context omitted.

Yes, there are a lot of people who are anti-science. As in they do not believe the scientific method is a good way to find truth. There are people today who are rejecting very basic science that was accepted over a century ago.

No, there aren't. Most people don't realize when they're being trolled by things like e.g. flat earth types. Go read one of the groups, it's a trolling meme largely turned into something by the internet + media. Thanks to social media even if let's say 0.1% of English speakers believe (or pretend to believe) something, that'd be 1.6 million people, so you can get a false impression, especially when the media takes th…

Post by ijk » Wed, Jun 04, 2025, 4:07 PM UTC

6stringmerc wrote: post #114

teruakohatu wrote: post #96

Earlier quoted context omitted.

> Like giving GPT a multiple-choice test on gibberish—it will pick something, and say it with its chest. If I gave a classroom of under grad students a multiple choice test where no answers were correct, I can almost guarantee almost all the tests would be filled out. Should GPT and other LLMs refuse to take a test? In my experience it will answer with the closest answer, even if none of the options are even remotely…

Yes, it should refuse. Humans have made progress by admitting when they don’t know something. Believing an LLM should be exempt from this boundary of “responsible knowledge” is an untenable path. As in, if you trust an ignorant LLM then by proxy you must trust a heart surgeon to perform your hip replacement.

Post by k__ » Wed, Jun 04, 2025, 4:17 PM UTC

TeMPOraL wrote: post #115

sebzim4500 wrote: post #97

Earlier quoted context omitted.

>Lately, I just steal embeddings from big models and slap a dumb classifier on top. Works better, runs faster, less drama. Sure but this is still indirectly using transformers.

Yes, but it's using the understanding they acquired to guide a more reliable tool, instead of also making them generate the final answer, which they're likely to hallucinate in this problem space.