Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting. (May 7
| Jan 23, 2024
0  |  Read Time 0 min
link
Publish Date
Number
reflection
abstract
CoT Explanations 不 faithful,通过在demonstration中增加bias features(总是为A答案)
Status
Done
Type
evaluation
Author
  • Valine
Catalog