News for hackers. Stuff that matters.
Re:Vision Language Models Are Biased by hkmaxpro on Wednesday June 04, 2025 @12:37AM (#44177276)
I think social biases (e.g. angry black women stereotype) in your paper is different from cognitive biases about facts (e.g. number of legs, whether lines are parallel) that OP is about.

Social biases are subjective. Facts are not.

Re:Vision Language Models Are Biased by rcxdude on Wednesday June 04, 2025 @05:13AM (#44178695)
As far as the model's concerned, there's not much difference. Social biases will tend to show up objectively in the training data because the training data is influenced by those biases (the same thing happens with humans, which how these biases can proliferate and persist).
Re:Vision Language Models Are Biased by vokhanhan25 on Wednesday June 04, 2025 @06:34AM (#44179237)
I see a clear difference. One is objective (only one correct answer), one is subjective (multiple plausible answers)