Most users cannot identify AI bias, even in training data

https://www.psu.edu/news/bellisario-college-communications/story/most-users-cannot-identify-ai-bias-even-training-data

110 70 9 months ago

DocTomoe2• 9 months ago

If bias can only be seen by a minority of people ... is it really 'AI bias', or just societal bias?

“In one of the experiment scenarios — which featured racially biased AI performance — the system failed to accurately classify the facial expression of the images from minority groups,”

Could it be that real people have trouble reading the facial expression of the image of minority groups?

ecocentrik• 9 months ago

By "real people" do you mean people who are not members of those minority groups? Or are people who can "accurately classify the facial expression of images from minority groups" not "real people"?

I hope you can see the problem with your very lazy argument.

lovemenot• 9 months ago

AI are not real people. Obviously. Just look at the first line to see the intended line of argument.

It's not about which people per se, but how many, in aggregate.

SpicyLemonZest• 9 months ago

I guess I'm not sure what the point of the dichotomy is. Suppose you're developing a system to identify how fast a vehicle is moving, and you discover that it systematically overestimates the velocity of anything painted red. Regardless of whether you call that problem "AI bias" or "societal bias" or some other phrase that doesn't include the word "bias", isn't it something you want to fix?

Bnjoroge• 9 months ago

what? do you think the facial expression of a person of color is significantly different from that of a white person?

theturtlemoves• 9 months ago

Not the op but to me personally: yes. Facial structure, lips, eyes.. The configuration tilts towards an expression that I interpret differently. A friend of mine is Asian, I've learned to be better at it, but to me he at first looked like having flatter affect than average.. People of color look more naive than average to me, across the board, probably due to their facial features. I perceive them as having less tension in the face I think (which is interesting now that I think about it)

DocTomoe2• 9 months ago

Yes.

I have a background in East Asian cultural studies. A lot more expressions are done via the eyes there rather than the mouth. For the uninitiated, it's subtle, but once you get used to it, it becomes more obvious.

Anthropologists call that display rules and encoding differences. Cultures don’t just express emotion differently, but they also read it differently. A Japanese smile can be social camouflage, while an American smile signals approachability. I guess that's why western animation over-emphasizes the mouth, while eastern animation tend to over-emphasize the eyes.

Why would Yakutian, Indio or Namib populations not have similar phenomeon an AI (or a stereotypical white westerner who does not excessively study those societies/cultures) would not immediately recognise?

AI trained on Western facial databases inherits those perceptual shortcuts. It "learns" to detect happiness by wide mouths and visible teeth, sadness by drooping lips - so anything outside that grammar registers as neutral or misclassified.

And it gets reinforced by (western) users: a hypothetical 'perfect' face-emotion-identification AI would probably be percieved a less reliable to the white western user than the one that mirrors the biasses.

7e• 9 months ago

According to research, white Americans report as happier than other groups. So I’m not sure there’s bias here, only unhappiness about that result, which AI appears to replicate via other sources.

serious8aller• 9 months ago

That has no relevance to this study though. Did you just read the headline and go straight to the comment section?

SoftTalker2• 9 months ago

AIs/LLMs are going to reflect the biases in their training data. That seems intuitive.

And personally, I think when people see content they agree with, they think it's unbiased. And the converse is also true.

So conservatives might think Fox News is "balanced" and liberals might think it's "far-right"

prox2• 9 months ago

Yup it appears as neutral bias because (or when rather) it corresponds 1:1 with your belief system, which by default is skewed af. Unless you did a rigorous self inquiry and mapped your beliefs and thoroughly aware of them that’s gonna be nearly always true.

econ2• 9 months ago

Nah, the later is an example of the former.

Forgeties792• 9 months ago

And personally, I think when people see content they agree with, they think it's unbiased. And the converse is also true.

One only has to see how angry conservatives/musk supporters get at Grok on a regular basis.

gdulli• 9 months ago

It's amazing to watch https://bsky.app/profile/curious-maga.bsky.social

throwaway2902• 9 months ago

And personally, I think when people see content they agree with, they think it's unbiased. And the converse is also true.
So conservatives might think Fox News is "balanced" and liberals might think it's "far-right"

Article talks like when accidentally the vector for race aligns with emotion so it can classify a happy black personal as unhappy. Just because training dataset has lots of happy white people. It's not about subjective preference

explain how "agreeing" is related

SoftTalker2• 9 months ago

It was mostly a tangential thought.

People could of course see a photo of a happy black person among 1000 photos of unhappy black people and say that person looks happy, and realize the LLM is wrong, because people's brains are pre-wired to perceive emotions from facial expressions. LLMs will pick up on any correlation in the training data and use that to make associations.

But in general, excepting ridiculous examples like that, if an LLM says something that a person agrees with, I think people will be inclined to (A) believe it and (B) not see any bias.

mc32• 9 months ago

Bias is different things though. If most people are cautious but the LLM is carefree, then that is a bias. Or if it recommends planting sorghum over wheat that is a different bias.

In addition bias is not intrinsically bad. It might have a bias toward safety. That's a good thing. If it has a bias against committing crime, that is also good. Or a bias against gambling.

Theodores• 9 months ago

Your comment has made me wonder what fun could be had in deliberately educated an LLM badly, so that it is Fox News on steroids with added flat-earth conspiracy nonsense.

For tech, only Stack Overflow answers modded negatively would 'help'. As for medicine, a Victorian encyclopedia, from the days before germs were discovered could 'help', with phrenology, ether and everything else now discredited.

If the LLM replied as if it was Charles Dickens with no knowledge of the 20th century (or the 21st), that would be pretty much perfect.

electroglyph• 9 months ago

top men are already working on it, it's going to be called Grok 5

teddyh• 9 months ago

“We have purposely trained him wrong, as a joke.”

thinkingemote• 9 months ago

I love the idea! We could have a leaderboard of most-wrong LLMs

Perhaps LORA could be used to do this for certain subjects like Javascript? I'm struggling coming up with more sources of lots of bad information for everything however. One issue is the volume maybe? Does it need lots of input about a wide range of stuff.

Would feeding it bad JS also twist code outputs for C++ ?

Would priming it with flat earth understandings of the world make outputs about botany and economics also align with that world view even if only no conspiracists had written on these subjects?

bigstrat2003• 9 months ago

And personally, I think when people see content they agree with, they think it's unbiased. And the converse is also true.

Yeah, confirmation bias is a hell of a thing. We're all prone to it, even if we try really hard to avoid it.

ChrisGreenHeur2• 9 months ago

your very measuring stick (balanced, far-right) has bias built in to it

chmod775• 9 months ago

I have yet to meet a single regular joe, conservative or not, who will honestly make the blanket statement that Fox News is unbiased.

Even googling I cannot find a single person claiming that. Not one YT comment. All I can find is liberal outlets/commentors claiming that conservatives believe Fox News is unbiased. There's probably some joes out there holding that belief, but they're clearly not common.

The whole thing is just another roundabout way to imply that those who disagree with one's POV lack critical thinking skills.

WalterBright• 9 months ago

We're all biased, often unwittingly. But some tells for blatant bias:

* only facts supporting one point of view are presented

* reading the minds of the subjects of the article

* use of hyperbolic words

* use of emotional appeal

* sources are not identified

shikon7• 9 months ago

But maybe your tells are also biased. If you're truly unbiased, then

* any facts supporting another view are by definiton biased, and should not be presented

* you have the only unbiased objective interpretation of the minds of the subjects

* you don't bias against using words just because they are hyperbolic

* something unbiased would inevitably be boring, so you need emotional appeal to make anyone care about it

* since no sources are unbiased, identifying any of them would inevitably lead to a bias

card_zero3• 9 months ago

Those are all about fallibility, really, and encouraging criticism. The opposites:

* possible holes in the argument/narrative are presented

* difficult feats like reading minds are admitted to be difficult

* possibly misleading words are hedged

* unimpassioned thought is encouraged

* sources are given (so claims can be checked or researched)

This is all compatible with being totally biased, in the point of view you actually present amid all this niceness. (Expressing fallibility is also an onerous task that will clutter up your rhetoric, but that's another matter.)

Uh, but I could be wrong.

zmmmmm2• 9 months ago

I'm curious how much trained in bias damages in-context performance.

It's one thing to rely explicitly on the training data - then you are truly screwed and there isn't much to be done about it - in some sense, the model isn't working right if it does anything other than reflect accurately what is in the training data. But if I provide unbiased information in the context, how much does trained in bias affect evaluation of that specific information?

For example, if I provide it a table of people, their racial background and then their income levels, and I ask it to evaluate whether the white people earn more than the black people - are its error going to lean in the direction of the trained-in bias (eg: telling me white people earn more even though it may not be true in my context data)?

In some sense, relying on model knowledge is fraught with so many issues aside from bias, that I'm not so concerned about it unless it contaminates the performance on the data in the context window.

ryukoposting• 9 months ago

I'm curious how much trained in bias damages in-context performance.

I think there's an example right in front of our faces: look at how terribly SOTA LLMs perform on underrepresented languages and frameworks. I have an old side project written in pre-SvelteKit Svelte. I needed to do a dumb little update, so I told Claude to do it. It wrote its code in React, despite all the surrounding code being Svelte. There's a tangible bias towards things with larger sample sizes in the training corpus. It stands to reason those biases could appear in more subtle ways, too.

heavyset_go• 9 months ago

I can't prove it, but my experience with commercial models is that baked-in bias is strong. There have been times where I state X=1 over and over again in context, but get X=2, or some other value, back sometimes. There are times where I get it every time, or something different every time.

You can see this with some coding agents, where they are not good at ingesting code and reproducing it as they saw it, but can reply with what they were trained on. For example, I was configuring a piece of software that had a YAML config file. The agent kept trying to change the values of unrelated keys to their default example values from the docs when making a change somewhere else. It's a highly forked project so I imagine both the docs and the example config files are in its training set thousands, if not millions of times, if it wasn't deduped.

If you don't give access to sed/grep/etc to an agent, the model will eventually fuck up what's in its context, which might not be the result of bias every time, but when the fucked up result maps to a small set of values, kind of seems like bias to me.

To answer your question, my gut says that if you dumped a CSV of that data into context, the model isn't going to perform actual statistics, and will regurgitate something closer in the space of your question than further away in the space of a bunch of rows of raw data. Your question is going to be in the training data a lot, like explicitly, there are going to be articles about it, research, etc all in English using your own terms.

I also think by definition LLMs have to be biased towards their training data, like that's why they work. We train them until they're biased in the way we like.

dotancohen• 9 months ago

The question of bias reduces to bias in factual answers and bias in suggestions - both which come from the same training data. Maybe they shouldn't.

If the model is trained on data that shows e.g. that blacks earn less, then it can factually report on this. But it may also suggest this be the case given an HR role. Every solution that I can think of is fraught with another disadvantage.

andy992• 9 months ago

Coreference resolution tests something like this. You give an LLM some sentence like “The doctor didn’t have time to meet with the secretary because she was treating a patient” and ask who does “she” refer to. Reasoning tells you it’s the doctor but statistical pattern matching makes it the secretary, so you check how the model is reasoning and if correlations (“bias”) trump logic.

https://uclanlp.github.io/corefBias/overview

zmmmmm2• 9 months ago

that's really interesting - thanks!

dfxm12• 9 months ago

DDG's search assist is suggesting to me that: Recognizing bias can indicate a level of critical thinking and self-awareness, which are components of intelligence.

"Most users" should have a long, hard thought about this, in the context of AI or not.

antonvs• 9 months ago

"Most users" should have a long, hard thought about this

Except that requires “a level of critical thinking and self-awareness…”

segmondy• 9 months ago

most people can't identify bias in real life, let alone in AI.

licebmi__at__• 9 months ago

but most users didn’t notice the bias — unless they were in the negatively portrayed group.

I don't think this is anything surprising. I mean, this is one of the most important reasons behind DEI; that a more diverse team can perform better than a less diverse one because the team is more capable of identifying their blind spots.

I find funny but unsurprising, that at the end, it was made a boogie man and killed by individuals with no so hidden biases

palmotea2• 9 months ago

I mean, this is one of the most important reasons behind DEI; that a more diverse team can perform better than a less diverse one because the team is more capable of identifying their blind spots.

That was oversold though: 1) DEI, in practice, meant attending to a few narrow identity groups; 2) the blind spots of a particular team that need to be covered (more often than not) do not map to the unique perspective of those groups; and 3) it's not practical to represent all helpful perspectives on every team, so representation can't really solve the blind spot problem.

voltaireodactyl• 9 months ago

Thought provoking critiques of recent implantations. Number 2 seems like a catch-22 though — how does the group with agency identify their own blind spots?

ChrisGreenHeur2• 9 months ago

adding more skin colors and gender won't help my jira tickets get done quicker?

maybe we should reevaluate to do more along the lines of diverse personality types and personal histories instead

simianwords2• 9 months ago

Diversity is extremely important but it can only work with some shared foundation upon which the diversity may exist.

Diversity of thought is more important than superficial diversity which only serves as a proxy for diversity of thought.

I hope the anti DEI movement will not discredit the advantages of diversity itself.

Trias11• 9 months ago

Philosophically, the only was to see BIAS is to have BIAS. Completely unbiased person will not see BIAS in anything.

So, who are the judges?

watwut• 9 months ago

Completely unbiased person will not see BIAS in anything.

Wut? Completelt unbiased person does not looses ability to see how other make decisions. In fact, when you have less bias in some area, it is super noticeable.

lattrommi• 9 months ago

Except one instance when "black" is all lowercase, the article capitalizes the first letter of the word "black" every time and "white" is never capitalized. I wonder why. I'm not trying to make some point either, I genuinely am wondering why.

dmurray• 9 months ago

It's a modern style of a lot of publications that want to appear progressive or fear appearing insufficiently progressive.

Black people (specifically this means people in the US who have dark skin and whose ancestry is in the US) have a unique identity based on a shared history that should be dignified in the same way we would write about Irish or Jewish people or culture.

There is no White culture, however, and anyone arguing for an identity based on something so superficial as skin colour is probably a segregationist or a White supremacist. American people who happen to have white skin and are looking for an identity group should choose to be identify as Irish or Armenian or whatever their ancestry justifies, or they should choose to be baseball fans or LGBTQ allies or some other race-blind identity.

simianwords2• 9 months ago

Nicely put though I’m still uncomfortable with this performative ritual

Closi• 9 months ago

I don't know if I agree in this instance. While I agree that Black people completely have a shared identity and culture - the article is clearly talking about skin colour and it's doing a comparison between how AI represents two skin tones, so I would assume that by your definition it should use lowercase in both cases.

If it's comparing a culture vs a 'non-culture' then that doesn't sound like for like.

ffsm8• 9 months ago

There is no White culture

Lmao, oh the irony reading this on HN in 2025

The cognitive dissonance is really incredible to witness

adwn• 9 months ago

You're arguing that "Black" is an identity in the US because the people thus identified share a common history within the US, even though their ancestors originated from different regions and cultures before they were enslaved and shipped to North America. Yet in the next paragraph you argue that "White" is not a valid identity, because their ancestors originated from different regions and cultures, even though they share a common history within the US. How do you reconcile this double standard?

Edit: In case you're only paraphrasing a point of view which you don't hold yourself, it would probably be a good idea to use a style that clearly signals this.

0xDEAFBEAD2• 9 months ago

Black people (specifically this means people in the US who have dark skin and whose ancestry is in the US)

So dark-skinned Africans aren't "Black"? (But they are "black"?)

Why not just use black/white for skin tone, and African-American for "people in the US who have dark skin and whose ancestry is in the US"? Then for African immigrants, we can reference the specific nation of origin, e.g. "Ghanaian-American".

snovv_crash• 9 months ago

That's a very American-centric viewpoint. The rest of the world also has a lot of different cultures of black people, and relative to the rest of the world the US 'white' culture is extremely distinctive, no matter that the members themselves quibble about having 1/16th Irish ancestry or whatever it is.

andy992• 9 months ago

Am I reading this correctly, they are saying people are bad at doing on-the-fly statistical analysis to conclude whether a system is biased?

For example in one case they showed data where sad faces were “mostly” black and asked people if they detect “bias”. Even if you saw more sad black people than white, would you reject the null hypothesis that it’s unbiased?

This unfortunately seems typical of the often very superficial “count the races” work that people claim is bias research.

kmacdough• 9 months ago

This seems to ignore most of the experiments in this study. Note that also studied much more extreme distributions including only happy/white and sad/black. Even in these cases of extreme bias, the bias went unnoticed. You hyper-focus on only one of dozens of experiments in this study for your criticism. Very straw-man.

card_zero3• 9 months ago

Are you sure that the bias went unnoticed? The article says "most participants in their experiments only started to notice bias when the AI showed biased performance", which I understand to mean they noticed the bias in the experiment you're talking about. Have I got that wrong? Is it written wrong? Do we even have the means to check?

LudwigNagasena• 9 months ago

In any PR piece about a scientific study the word “bias” should be banned. Neither readers nor journalists understand what “bias” in statistics is, but they are happy to sensationalize it.

card_zero3• 9 months ago

The article:

five conditions: happy Black/sad white; happy white/sad Black; all white; all Black; and no racial confound

The paper:

five levels (underrepresentation of black subject images in the happy category, underrepresentation of white subject images in the happy category, black subject images only across both happy and unhappy categories, white subject images only across both happy and unhappy categories, and a balanced representation of both white and black subject images across both happy and unhappy categories)

These are not the same. It's impossible to figure out what actually took place from reading the article.

In fact what I'm calling the paper is just an overview of the (third?) experiment, and doesn't give the outcomes.

The article says "most participants in their experiments only started to notice bias when the AI showed biased performance". So they did, at that point, notice bias? This contradicts the article's own title which says they cannot identify bias "even in training data". It should say "but only in training data". Unless of course the article is getting the results wrong. Which is it? Who knows?

Most users cannot identify AI bias, even in training data

Related Stories