Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (2025)

> Our findings consistently challenge the prevailing narrative that intermediate tokens constitute a semantically meaningful reasoning process. First, we observe a pronounced lack of correlation between solution correctness and trace validity—models frequently produce invalid reasoning traces even when they arrive at correct solutions. Second, and more strikingly, models trained on corrupted or semantically irrelevant traces achieve performance comparable to, and often exceeding, that of models trained on correct traces, especially on out-of-distribution tasks.

[1]: https://arxiv.org/abs/2504.09762

Because the field of artificial "intelligence" is constructed around the idea of applying psychological metaphors to computational systems (a very powerful idea!) it's almost a worst case scenario for these people.

Suddenly, they're reversing the metaphors and applying computational schema to psychological processes ("aren't we really just stochastic parrots ourselves?!"); or, like here, they find themselves surprised and confused when they stumble across the natural boundaries of the metaphor experimentally.

It's because they never had sight of the boundaries in the first place and maybe never can quite see them. The words only make sense to them as literal equivalence, and so their surprise when they run into stuff like this is earnest and deep.

When doing the paper we noticed that models are very good at generating post-hoc plausible CoT, which to me knowledge can happen quite often with relatively easy tasks.

You might be interested in reading this other paper that came out after ours: https://arxiv.org/abs/2507.05246

if not, then there's certainly some bearing, but not necessarily in how we read the tokens as text