这个有点类似给快思考加了一层慢思考

像 GPT 这样的 LLM 能否像人类一样从错误中吸取教训并自我反省?

答案是肯定的,该方法使 HotPotQA 的准确率提高了 33-35%!

Lior: Can LLMs like GPT learn from their mistakes and self-reflect just like humans?

The answer is yes and the method resulted in 33-35% accuracy improvement on HotPotQA!

Paper:
Code:

https://arxiv.org/abs/2303.11366https://github.com/noahshinn024/reflexion
 
 
Back to Top