AI CoT Reasoning Is Often Unfaithful
Is Chain-of-Thought Reasoning of LLMs a Mirage?
... Our results reveal that CoT reasoning is a brittle mirage that vanishes when it is pushed beyond training distributions. This work offers a deeper understanding of why and when CoT reasoning fails, emphasizing the ongoing challenge of achieving genuine and... See more
The LLMentalist Effect: How Chat-Based Large Language Models Replicate the Mechanisms of a Psychic’s Con
Baldur Bjarnasonsoftwarecrisis.devWhy language models hallucinate
openai.com