zlacker

>>kevema+(OP)
>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time.

Some of the reasoning:

>Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones and a tendency for images portraying different professions to align with Western gender stereotypes. Finally, even when we focus generations away from people, our preliminary analysis indicates Imagen encodes a range of social and cultural biases when generating images of activities, events, and objects. We aim to make progress on several of these open challenges and limitations in future work.

Really sad that breakthrough technologies are going to be withheld due to our inability to cope with the results.

>>daenz+b5
This raises some really interesting questions.

We certainly don't want to perpetuate harmful stereotypes. But is it a flaw that the model encodes the world as it really is, statistically, rather than as we would like it to be? By this I mean that there are more light-skinned people in the west than dark, and there are more women nurses than men, which is reflected in the model's training data. If the model only generates images of female nurses, is that a problem to fix, or a correct assessment of the data?

If some particular demographic shows up in 51% of the data but 100% of the model's output shows that one demographic, that does seem like a statistics problem that the model could correct by just picking less likely "next token" predictions.

Also, is it wrong to have localized models? For example, should a model for use in Japan conform to the demographics of Japan, or to that of the world?

>>tines+E7
It depends on whether you'd like the model to learn casual or correlative relationships.

If you want the model to understand what a "nurse" actually is, then it shouldn't be associated with female.

If you want the model to understand how the word "nurse" is usually used, without regard for what a "nurse" actually is, then associating it with female is fine.

The issue with a correlative model is that it can easily be self-reinforcing.

>>karpie+m9
Additionally, if you optimize for most-likely-as-best, you will end up with the stereotypical result 100% of the time, instead of in proportional frequency to the statistics.

Put another way, when we ask for an output optimized for "nursiness", is that not a request for some ur stereotypical nurse?

>>jdashg+9b
You could stipulate that it roll a die based on percentage results - if 70% of Americans are "white", then 70% of the time show a white person - 13% of the time the result should be black, etc.

That's excessively simplified but wouldn't this drop the stereotype and better reflect reality?

>>ar_lan+Lg
No, because a user will see a particular image not the statistically ensemble. It will at times show an Eskimo without a hand because they do statistically exist. But the user definitely does not want that.