Progressive-Hint Prompting Improves Reasoning in Large Language Models. (arXiv:2304.09797v2 [cs.CL] UPDATED)

The performance of Large Language Models (LLMs) in reasoning tasks depends
heavily on prompt design, with Chain-of-Thought (CoT) and self-consistency
being critical methods that enhance this ability. However, these methods do not
fully exploit the answers generated by the LLM to guide subsequent responses.
This paper proposes a new prompting method, named Progressive-Hint Prompting
(PHP), that enables automatic multiple interactions between users and LLMs by
using previously generated answers as hints to progressively guide toward the
correct answers. PHP is …

arxiv design exploit generated guide language language models large language models llm llms paper performance prompt prompting reasoning responses thought