@inproceedings{hsieh-etal-2024-automatic,
title = "Automatic Engineering of Long Prompts",
author = "Hsieh, Cho-Jui and
Si, Si and
Yu, Felix and
Dhillon, Inderjit",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.634",
doi = "10.18653/v1/2024.findings-acl.634",
pages = "10672--10685",
abstract = "Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy, often comprising hundreds of lines and thousands of tokens, and their design often requires considerable human effort. Recent research has explored automatic prompt engineering for short prompts, typically consisting of one or a few sentences. However, the automatic design of long prompts remains a challenging problem due to its immense search space. In this paper, we propose an algorithm named Automated Prompt Engineering Xpert (APEX), a novel algorithm that automatically improves long prompts. Leveraging a greedy algorithm with beam-search for efficiency, APEX utilizes search history to significantly enhance the effectiveness of LLM-based mutation in its search process. Our results show that APEX achieves an average of 9.2{\%} accuracy gain on eight tasks in Big Bench Hard and a consistent improvements on GSM8K with various models, highlighting the significance of automating prompt designs to fully harness the capabilities of LLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsieh-etal-2024-automatic">
<titleInfo>
<title>Automatic Engineering of Long Prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cho-Jui</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inderjit</namePart>
<namePart type="family">Dhillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy, often comprising hundreds of lines and thousands of tokens, and their design often requires considerable human effort. Recent research has explored automatic prompt engineering for short prompts, typically consisting of one or a few sentences. However, the automatic design of long prompts remains a challenging problem due to its immense search space. In this paper, we propose an algorithm named Automated Prompt Engineering Xpert (APEX), a novel algorithm that automatically improves long prompts. Leveraging a greedy algorithm with beam-search for efficiency, APEX utilizes search history to significantly enhance the effectiveness of LLM-based mutation in its search process. Our results show that APEX achieves an average of 9.2% accuracy gain on eight tasks in Big Bench Hard and a consistent improvements on GSM8K with various models, highlighting the significance of automating prompt designs to fully harness the capabilities of LLMs.</abstract>
<identifier type="citekey">hsieh-etal-2024-automatic</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.634</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.634</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10672</start>
<end>10685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Engineering of Long Prompts
%A Hsieh, Cho-Jui
%A Si, Si
%A Yu, Felix
%A Dhillon, Inderjit
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F hsieh-etal-2024-automatic
%X Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy, often comprising hundreds of lines and thousands of tokens, and their design often requires considerable human effort. Recent research has explored automatic prompt engineering for short prompts, typically consisting of one or a few sentences. However, the automatic design of long prompts remains a challenging problem due to its immense search space. In this paper, we propose an algorithm named Automated Prompt Engineering Xpert (APEX), a novel algorithm that automatically improves long prompts. Leveraging a greedy algorithm with beam-search for efficiency, APEX utilizes search history to significantly enhance the effectiveness of LLM-based mutation in its search process. Our results show that APEX achieves an average of 9.2% accuracy gain on eight tasks in Big Bench Hard and a consistent improvements on GSM8K with various models, highlighting the significance of automating prompt designs to fully harness the capabilities of LLMs.
%R 10.18653/v1/2024.findings-acl.634
%U https://aclanthology.org/2024.findings-acl.634
%U https://doi.org/10.18653/v1/2024.findings-acl.634
%P 10672-10685
Markdown (Informal)
[Automatic Engineering of Long Prompts](https://aclanthology.org/2024.findings-acl.634) (Hsieh et al., Findings 2024)
ACL
- Cho-Jui Hsieh, Si Si, Felix Yu, and Inderjit Dhillon. 2024. Automatic Engineering of Long Prompts. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10672–10685, Bangkok, Thailand. Association for Computational Linguistics.