@inproceedings{fereidouni-etal-2024-grounded,
title = "Grounded Language Agent for Product Search via Intelligent Web Interactions",
author = "Fereidouni, Moghis and
Mosharrof, Adib and
Siddique, A.b.",
editor = "Kumar, Sachin and
Balachandran, Vidhisha and
Park, Chan Young and
Shi, Weijia and
Hayati, Shirley Anugrah and
Tsvetkov, Yulia and
Smith, Noah and
Hajishirzi, Hannaneh and
Kang, Dongyeop and
Jurgens, David",
booktitle = "Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.customnlp4u-1.7",
pages = "63--75",
abstract = "Recent research has focused on developing agents powered by large language models (LLMs) to accomplish complex high-level user intents. However, employing LLMs with billions of parameters (e.g., GPT-4) may incur substantial costs on top of handcrafting extensive prompts. To address this, we introduce a Grounded Language Agent for Intelligent Web Interactions, named GLAINTEL. GLAINTEL employs Flan-T5 as its backbone and is flexible in training in various settings: unsupervised learning, supervised learning, and unsupervised domain adaptation. Specifically, we tackle both the challenge of learning without human demonstrations and the opportunity to leverage human demonstrations effectively when those are available. Additionally, we explore unsupervised domain adaptation for cases where demonstrations are limited to a specific domain. Experimental evaluations across diverse setups demonstrate the effectiveness of GLAINTEL in unsupervised settings, outperforming in-context learning-based approaches that employ larger models with up to 540 billion parameters. Surprisingly, behavioral cloning-based methods that straightforwardly use human demonstrations do not outperform unsupervised variants of GLAINTEL. Additionally, we show that combining human demonstrations with reinforcement learning-based training yields results comparable to methods utilizing GPT-4. The code is available at: https://github.com/MultifacetedNLP/Web-Agents-Unsupervised",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fereidouni-etal-2024-grounded">
<titleInfo>
<title>Grounded Language Agent for Product Search via Intelligent Web Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moghis</namePart>
<namePart type="family">Fereidouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adib</namePart>
<namePart type="family">Mosharrof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A.b.</namePart>
<namePart type="family">Siddique</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>Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirley</namePart>
<namePart type="given">Anugrah</namePart>
<namePart type="family">Hayati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyeop</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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>Recent research has focused on developing agents powered by large language models (LLMs) to accomplish complex high-level user intents. However, employing LLMs with billions of parameters (e.g., GPT-4) may incur substantial costs on top of handcrafting extensive prompts. To address this, we introduce a Grounded Language Agent for Intelligent Web Interactions, named GLAINTEL. GLAINTEL employs Flan-T5 as its backbone and is flexible in training in various settings: unsupervised learning, supervised learning, and unsupervised domain adaptation. Specifically, we tackle both the challenge of learning without human demonstrations and the opportunity to leverage human demonstrations effectively when those are available. Additionally, we explore unsupervised domain adaptation for cases where demonstrations are limited to a specific domain. Experimental evaluations across diverse setups demonstrate the effectiveness of GLAINTEL in unsupervised settings, outperforming in-context learning-based approaches that employ larger models with up to 540 billion parameters. Surprisingly, behavioral cloning-based methods that straightforwardly use human demonstrations do not outperform unsupervised variants of GLAINTEL. Additionally, we show that combining human demonstrations with reinforcement learning-based training yields results comparable to methods utilizing GPT-4. The code is available at: https://github.com/MultifacetedNLP/Web-Agents-Unsupervised</abstract>
<identifier type="citekey">fereidouni-etal-2024-grounded</identifier>
<location>
<url>https://aclanthology.org/2024.customnlp4u-1.7</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>63</start>
<end>75</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounded Language Agent for Product Search via Intelligent Web Interactions
%A Fereidouni, Moghis
%A Mosharrof, Adib
%A Siddique, A.b.
%Y Kumar, Sachin
%Y Balachandran, Vidhisha
%Y Park, Chan Young
%Y Shi, Weijia
%Y Hayati, Shirley Anugrah
%Y Tsvetkov, Yulia
%Y Smith, Noah
%Y Hajishirzi, Hannaneh
%Y Kang, Dongyeop
%Y Jurgens, David
%S Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F fereidouni-etal-2024-grounded
%X Recent research has focused on developing agents powered by large language models (LLMs) to accomplish complex high-level user intents. However, employing LLMs with billions of parameters (e.g., GPT-4) may incur substantial costs on top of handcrafting extensive prompts. To address this, we introduce a Grounded Language Agent for Intelligent Web Interactions, named GLAINTEL. GLAINTEL employs Flan-T5 as its backbone and is flexible in training in various settings: unsupervised learning, supervised learning, and unsupervised domain adaptation. Specifically, we tackle both the challenge of learning without human demonstrations and the opportunity to leverage human demonstrations effectively when those are available. Additionally, we explore unsupervised domain adaptation for cases where demonstrations are limited to a specific domain. Experimental evaluations across diverse setups demonstrate the effectiveness of GLAINTEL in unsupervised settings, outperforming in-context learning-based approaches that employ larger models with up to 540 billion parameters. Surprisingly, behavioral cloning-based methods that straightforwardly use human demonstrations do not outperform unsupervised variants of GLAINTEL. Additionally, we show that combining human demonstrations with reinforcement learning-based training yields results comparable to methods utilizing GPT-4. The code is available at: https://github.com/MultifacetedNLP/Web-Agents-Unsupervised
%U https://aclanthology.org/2024.customnlp4u-1.7
%P 63-75
Markdown (Informal)
[Grounded Language Agent for Product Search via Intelligent Web Interactions](https://aclanthology.org/2024.customnlp4u-1.7) (Fereidouni et al., CustomNLP4U 2024)
ACL
- Moghis Fereidouni, Adib Mosharrof, and A.b. Siddique. 2024. Grounded Language Agent for Product Search via Intelligent Web Interactions. In Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U), pages 63–75, Miami, Florida, USA. Association for Computational Linguistics.