Achieving >97 Better Reasoners
arxiv(2024)
摘要
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, including understanding
errors, calculation errors and process errors (e.g., missing-step and
hallucinations). Subsequently, our in-depth analyses among various error types
show that deeply understanding the whole problem is critical in addressing
complicated reasoning tasks. Motivated by this, we propose a
simple-yet-effective method, namely Deeply Understanding the Problems (DUP), to
enhance the LLMs' reasoning abilities. The core of our method is to encourage
the LLMs to deeply understand the problems and leverage the key problem-solving
information for better reasoning. Extensive experiments on 10 diverse reasoning
benchmarks show that our DUP method consistently outperforms the other
counterparts by a large margin. More encouragingly, DUP achieves a new SOTA
result on the GSM8K benchmark, with an accuracy of 97.1
setting.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要