@inproceedings{lo-etal-2023-hierarchical,
title = "Hierarchical Prompting Assists Large Language Model on Web Navigation",
author = "Lo, Robert and
Sridhar, Abishek and
Xu, Frank and
Zhu, Hao and
Zhou, Shuyan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.685",
doi = "10.18653/v1/2023.findings-emnlp.685",
pages = "10217--10244",
abstract = "Large language models (LLMs) struggle on processing complicated observations in interactive decision making. To alleviate this issue, we propose a simple hierarchical prompting approach. Diverging from previous prompting approaches that always put the full observation (a web page) to the prompt, we propose to first construct an action-aware observation which is more condensed and relevant with a dedicated Summarizer prompt. The Actor prompt then predicts the next action based on the summarized history. While our method has broad applicability, we particularly demonstrate its efficacy in the complex domain of web navigation where a full observation often contains redundant and irrelevant information. Our approach outperforms the previous state-of-the-art prompting mechanism with the same LLM by 6.2{\%} on task success rate, demonstrating its potential on interactive decision making tasks with long observation traces.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lo-etal-2023-hierarchical">
<titleInfo>
<title>Hierarchical Prompting Assists Large Language Model on Web Navigation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abishek</namePart>
<namePart type="family">Sridhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) struggle on processing complicated observations in interactive decision making. To alleviate this issue, we propose a simple hierarchical prompting approach. Diverging from previous prompting approaches that always put the full observation (a web page) to the prompt, we propose to first construct an action-aware observation which is more condensed and relevant with a dedicated Summarizer prompt. The Actor prompt then predicts the next action based on the summarized history. While our method has broad applicability, we particularly demonstrate its efficacy in the complex domain of web navigation where a full observation often contains redundant and irrelevant information. Our approach outperforms the previous state-of-the-art prompting mechanism with the same LLM by 6.2% on task success rate, demonstrating its potential on interactive decision making tasks with long observation traces.</abstract>
<identifier type="citekey">lo-etal-2023-hierarchical</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.685</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.685</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10217</start>
<end>10244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Prompting Assists Large Language Model on Web Navigation
%A Lo, Robert
%A Sridhar, Abishek
%A Xu, Frank
%A Zhu, Hao
%A Zhou, Shuyan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lo-etal-2023-hierarchical
%X Large language models (LLMs) struggle on processing complicated observations in interactive decision making. To alleviate this issue, we propose a simple hierarchical prompting approach. Diverging from previous prompting approaches that always put the full observation (a web page) to the prompt, we propose to first construct an action-aware observation which is more condensed and relevant with a dedicated Summarizer prompt. The Actor prompt then predicts the next action based on the summarized history. While our method has broad applicability, we particularly demonstrate its efficacy in the complex domain of web navigation where a full observation often contains redundant and irrelevant information. Our approach outperforms the previous state-of-the-art prompting mechanism with the same LLM by 6.2% on task success rate, demonstrating its potential on interactive decision making tasks with long observation traces.
%R 10.18653/v1/2023.findings-emnlp.685
%U https://aclanthology.org/2023.findings-emnlp.685
%U https://doi.org/10.18653/v1/2023.findings-emnlp.685
%P 10217-10244
Markdown (Informal)
[Hierarchical Prompting Assists Large Language Model on Web Navigation](https://aclanthology.org/2023.findings-emnlp.685) (Lo et al., Findings 2023)
ACL