推论
计算机科学
背景(考古学)
认知科学
基于案例的推理
人工智能
认知心理学
心理学
古生物学
生物
作者
Boshi Wang,Sewon Min,Xiang Deng,Jiaming Shen,You Wu,Luke Zettlemoyer,Huan Sun
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:4
标识
DOI:10.48550/arxiv.2212.10001
摘要
Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series of reasoning steps in the demonstrations. Despite its success, there is still little understanding of what makes CoT prompting effective and which aspects of the demonstrated reasoning steps contribute to its performance. In this paper, we show that CoT reasoning is possible even with invalid demonstrations - prompting with invalid reasoning steps can achieve over 80-90% of the performance obtained using CoT under various metrics, while still generating coherent lines of reasoning during inference. Further experiments show that other aspects of the rationales, such as being relevant to the query and correctly ordering the reasoning steps, are much more important for effective CoT reasoning. Overall, these findings both deepen our understanding of CoT prompting, and open up new questions regarding LLMs' capability to learn to reason in context.
科研通智能强力驱动
Strongly Powered by AbleSci AI