@inproceedings{yang-etal-2024-alignedcot,
title = "{A}ligned{C}o{T}: Prompting Large Language Models via Native-Speaking Demonstrations",
author = "Yang, Zhicheng and
Huang, Yinya and
Xiong, Jing and
Feng, Liang and
Liang, Xiaodan and
Wang, Yiwei and
Tang, Jing",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.163",
pages = "2857--2896",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-alignedcot">
<titleInfo>
<title>AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhicheng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinya</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiwei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">yang-etal-2024-alignedcot</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.163</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2857</start>
<end>2896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
%A Yang, Zhicheng
%A Huang, Yinya
%A Xiong, Jing
%A Feng, Liang
%A Liang, Xiaodan
%A Wang, Yiwei
%A Tang, Jing
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F yang-etal-2024-alignedcot
%X 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.
%U https://aclanthology.org/2024.findings-emnlp.163
%P 2857-2896
Markdown (Informal)
[AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations](https://aclanthology.org/2024.findings-emnlp.163) (Yang et al., Findings 2024)
ACL
- Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, and Jing Tang. 2024. AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2857–2896, Miami, Florida, USA. Association for Computational Linguistics.