AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zhicheng, Huang, Yinya, Xiong, Jing, Feng, Liang, Liang, Xiaodan, Wang, Yiwei, Tang, Jing
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913534963613696
author Yang, Zhicheng
Huang, Yinya
Xiong, Jing
Feng, Liang
Liang, Xiaodan
Wang, Yiwei
Tang, Jing
author_facet Yang, Zhicheng
Huang, Yinya
Xiong, Jing
Feng, Liang
Liang, Xiaodan
Wang, Yiwei
Tang, Jing
contents Large Language Models prompting, such as using in-context demonstrations, is a mainstream technique for invoking LLMs to perform high-performance and solid complex reasoning (e.g., mathematical reasoning, commonsense reasoning), and has the potential for further human-machine collaborative scientific findings. However, current LLMs are delicate and elusive in prompt words and styles. And there is an unseen gap between LLM understanding and human-written prompts. This paper introduces Alignedcot, an LLM-acquainted prompting technique that includes proficient ``native-speaking'' in in-context learning for the LLMs. Specifically, it achieves consistent and correct step-wise prompts in zero-shot scenarios by progressively probing, refining, and formatting the LLM chain of thoughts so that free from handcrafted few-shot demonstrations while maintaining the prompt quality. We conduct experiments on mathematical reasoning and commonsense reasoning. We find that LLMs with Alignedcot perform significantly superior to them with human-crafted demonstrations. We further apply Alignedcot for rewriting the GSM8K training set, resulting in a GSM8K-Align dataset. We observe its benefits for retrieval augmented generation. The code and data can be found at https://github.com/yangzhch6/AlignedCoT.
format Preprint
id arxiv_https___arxiv_org_abs_2311_13538
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
Yang, Zhicheng
Huang, Yinya
Xiong, Jing
Feng, Liang
Liang, Xiaodan
Wang, Yiwei
Tang, Jing
Artificial Intelligence
Machine Learning
Large Language Models prompting, such as using in-context demonstrations, is a mainstream technique for invoking LLMs to perform high-performance and solid complex reasoning (e.g., mathematical reasoning, commonsense reasoning), and has the potential for further human-machine collaborative scientific findings. However, current LLMs are delicate and elusive in prompt words and styles. And there is an unseen gap between LLM understanding and human-written prompts. This paper introduces Alignedcot, an LLM-acquainted prompting technique that includes proficient ``native-speaking'' in in-context learning for the LLMs. Specifically, it achieves consistent and correct step-wise prompts in zero-shot scenarios by progressively probing, refining, and formatting the LLM chain of thoughts so that free from handcrafted few-shot demonstrations while maintaining the prompt quality. We conduct experiments on mathematical reasoning and commonsense reasoning. We find that LLMs with Alignedcot perform significantly superior to them with human-crafted demonstrations. We further apply Alignedcot for rewriting the GSM8K training set, resulting in a GSM8K-Align dataset. We observe its benefits for retrieval augmented generation. The code and data can be found at https://github.com/yangzhch6/AlignedCoT.
title AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2311.13538