Improving Interactive In-Context Learning from Natural Language Feedback

Improving Interactive In-Context Learning from Natural Language Feedback(arxiv.org)

1 points by revv00 40 days ago | 1 comment

revv00 40 days ago |

Interesting paper, it reminds me how we human improving our math problem solving capability. But those efficient guys use few problems(and reasoning trajectories) to build their solving skills, how to build this effective human training process into LLM's?

revv00 40 days ago |

Interesting paper, it reminds me how we human improving our math problem solving capability. But those efficient guys use few problems(and reasoning trajectories) to build their solving skills, how to build this effective human training process into LLM's?