vokhanhan25

Models can be biased, but it doesn't seem like it should be a reason to get the answer wrong, right? Humans have biases too, but we don't get those simple questions wrong

I see a clear difference. One is objective (only one correct answer), one is subjective (multiple plausible answers)

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

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.

Agreed. It would be even more dangerous if we were talking about weird edge cases in self-driving cars or medical imaging.

Not really. Rather, the model is still overconfident in what it has learned, the question is if it is trained only to do counting without relying on knowledge, can it do this?

Please check Table 3 in the paper. Birds (2 legs) have only 1%, while Mammals (4 legs) have 2.5%

I think LLMs can solve puzzles pretty well because the thinking ability of current models on text is quite good. Moreover, puzzles are not easy for a 7-year-old like this benchmark.

This paper explores a different aspect of the limitations of VLMs compared to the paper VLMs are Blind (https://vlmsareblind.github.io). While in VLMs are Blind, o3 achieved 90% accuracy (https://openai.com/index/thinking-with-images), on similarly easy tasks using the counterfactual images from VLMs are Biased, o3 only reached 18.5%.

This may indicate that while VLMs might possess the necessary capability, their strong biases can cause them to overlook important cues, and their overconfidence in their own knowledge can lead to incorrect answers.