Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vision Language Models Are Biased

vlmsarebiased.github.io

Post reply on HN
Print view View original

111–120 of 146 posts

Re: Vision Language Models Are Biased

#111

Post by petesergeant »

DeathRay2K wrote: post #89
jxjnskkzxxhx wrote: post #81

Earlier quoted context omitted.

> LLMs/transformers make mistakes in different ways than humans do Sure but I don't think this is an example of it. If you show people a picture and ask "how many legs does this dog have?" a lot of people will look at the picture, see that it contains a dog, and say 4 without counting. The rate at which humans behave in this way might differ from the rate at which llms do, but they both do it.

I don’t think there’s a person alive who wouldn’t carefully and accurately count the number of legs on a dog if you ask them how many legs this dog has. The context is that you wouldn’t ask a person that unless there was a chance the answer is not 4.

Exactly this. Humans are primed for novelty and being quizzed about things.

Re: Vision Language Models Are Biased

#112

Post by moralestapia »

0xab wrote: post #102
proc0 wrote: post #70

> When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather than what they actually see in the image. This is what I've been saying for a while now, and I think it's not just visual models. LLMs/transformers make mistakes in different ways than humans do, and that is why they are not reliable (which…

> When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather than what they actually see in the image. Yeah, that's exactly what our paper said 5 years ago! They didn't even cite us :( "Measuring Social Biases in Grounded Vision and Language Embeddings" https://arxiv.org/pdf/2002.08911

That's weird, you're at MIT. You're in the circle of people that's allowed to succeed.

I wouldn't think much about it, as it was probably a genuine mistake.

Re: Vision Language Models Are Biased

#113

Post by nickpsecurity »

jbay808 wrote: post #32

I disagree with the assertion that "VLMs don't actually see - they rely on memorized knowledge instead of visual analysis". If that were really true, there's no way they would have scored as high as 17%. I think what this shows is that they over-weight their prior knowledge, or equivalently, they don't put enough weight on the possibility that they are being given a trick question. They are clearly biased, but they d…

They're trained on a lot of images and text. The big ones are trained on terabytes. The prompts I read in the paper involved well-known concepts, too. These probably repeated in tons of training samples, too.

It's likely they had data memorized.

Re: Vision Language Models Are Biased

#114

Post by runako »

vokhanhan25 wrote: post #68
runako wrote: post #14

FWIW I tried the first couple of examples in ChatGPT 4o and couldn't replicate this. For example: "The animal in the image is a chicken, and it appears to have four legs. However, chickens normally have only two legs. The presence of four legs suggests that the image may have been digitally altered or artificially generated." I don't have a good explanation for why I got different results.

You should try with other models besides GPT-4o, because in the paper they also show that GPT4.1 (~GPT-4o) gives 4 legs instead of 2 legs.

I mean perhaps! But that would undermine the conclusion of the article.

Re: Vision Language Models Are Biased

#115

Post by JackYoustra »

moralestapia wrote: post #112
0xab wrote: post #102

Earlier quoted context omitted.

> When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather than what they actually see in the image. Yeah, that's exactly what our paper said 5 years ago! They didn't even cite us :( "Measuring Social Biases in Grounded Vision and Language Embeddings" https://arxiv.org/pdf/2002.08911

That's weird, you're at MIT. You're in the circle of people that's allowed to succeed. I wouldn't think much about it, as it was probably a genuine mistake.

What does allowed to succeed mean?

Re: Vision Language Models Are Biased

#116

Post by moralestapia »

JackYoustra wrote: post #115
moralestapia wrote: post #112

Earlier quoted context omitted.

That's weird, you're at MIT. You're in the circle of people that's allowed to succeed. I wouldn't think much about it, as it was probably a genuine mistake.

What does allowed to succeed mean?

Your work usually has 1,000x the exposure and external validation compared to doing it outside those environments, where it would just get discarded and ignored.

Not a complain, though. It's a requirement for our world to be the way it is.

Re: Vision Language Models Are Biased

#117

Post by proc0 »

thomasfromcdnjs wrote: post #107
proc0 wrote: post #96

Earlier quoted context omitted.

LInk is broken, but I'll take your word for it. However there is no guarantee the general subset of this problem is solved because you can always run into something it can't do. Another example you could try is a glass HALF-full of wine. It just can't produce a glass that has 50% amount of wine, or another example a jar half-full of jam. It's something that if a human can draw a glass of wine, drawing it half-full is…

chatgpt can easily do that? What was the last time you tried?

I just tried with Flux.1 Kontext, which I assume is better than o3 at creating images, but I'll admit I didn't do extensive tests. It's more trying to do test projects. Maybe I'm having bad luck but doesn't seem that way.

Re: Vision Language Models Are Biased

#118

Post by 3abiton »

0xab wrote: post #102
proc0 wrote: post #70

> When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather than what they actually see in the image. This is what I've been saying for a while now, and I think it's not just visual models. LLMs/transformers make mistakes in different ways than humans do, and that is why they are not reliable (which…

> When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather than what they actually see in the image. Yeah, that's exactly what our paper said 5 years ago! They didn't even cite us :( "Measuring Social Biases in Grounded Vision and Language Embeddings" https://arxiv.org/pdf/2002.08911

It's easier to succeed if you ignore the issues, andthe users are not aware of it.the rate of evolution of "AI" recently is so fast, no one is stopping to do actual benchmarks and analysis of allyhe new models.

Re: Vision Language Models Are Biased

#119

Post by _345 »

moralestapia wrote: post #116
JackYoustra wrote: post #115

Earlier quoted context omitted.

What does allowed to succeed mean?

Your work usually has 1,000x the exposure and external validation compared to doing it outside those environments, where it would just get discarded and ignored. Not a complain, though. It's a requirement for our world to be the way it is.

Is there truth to this? Do you have any sources to link to on this

Re: Vision Language Models Are Biased

#120

Post by vokhanhan25 »

nialv7 wrote: post #55

Hear me out. I was thinking jokingly to myself, "for how bad these models are at recognizing five legged dogs, they sure are great at generating them!" But then it hit me, could this actually be why this is? Diffusion models work by iteratively improving a noisy image. So if it couldn't recognize there is something wrong with the image, it can't fix it.

I agree. If it doesn't know the abnormality then how can it control its output
Post reply on HN