Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
- In this work, we show that unfaithful CoT also occurs on naturally worded, non-adversarial prompts without adding artificial biases or editing model outputs.
- We find that when separately presented with the questions "Is X bigger than Y?
Unverified
- In this work, we show that unfaithful CoT also occurs on naturally worded, non-adversarial prompts without adding artificial biases or editing model outputs.
- We find that when separately presented with the questions "Is X bigger than Y?
Sources: Arxiv