flyingpumba
Re:Chain-of-Thought Reasoning in the Wild Is Not Always Faithful
on Wednesday August 19, 2026 @03:55PM (#49366375)
First author here, surprised to see the paper in HN! :)
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
Re:Chain-of-Thought Reasoning in the Wild Is Not Always Faithful
on Wednesday August 19, 2026 @03:34PM (#49366163)
First author here, happy to answer questions