Improve multi-hop reasoning in LLMs by learning from rich human feedback
AWS Machine Learning
APRIL 27, 2023
The final dataset contains feedback for 1,565 samples from StrategyQA and 796 examples for Sports Understanding. In each case, the model was prompted with k in-context examples containing question, answer, and explanation, followed by the test question. It’s worth noting that some examples may have more than one error type.
Let's personalize your content