Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Perfect Reasoners

arXiv:2404.14963v1 Announce Type: new
Abstract: Chain of Thought prompting strategy has enhanced the performance of Large Language Models (LLMs) across various NLP tasks. However, it still has shortcomings when dealing with complex reasoning tasks, following~\citet{cot_wei}, including understanding errors, calculation errors and process errors (e.g. missing-step and hallucinations). Subsequently, Our in-depth analysis of various error types has found that deeply understanding the whole problem is critical in addressing complicated reasoning tasks. In this paper, we proposed a novel prompt strategy called …

abstract arxiv chain of thought cs.ai cs.cl errors hallucinations however language language models large language large language models llms nlp performance process prompting reasoning strategy tasks thought type understanding