@inproceedings{gur-etal-2023-understanding,
title = "Understanding {HTML} with Large Language Models",
author = "Gur, Izzeddin and
Nachum, Ofir and
Miao, Yingjie and
Safdari, Mustafa and
Huang, Austin and
Chowdhery, Aakanksha and
Narang, Sharan and
Fiedel, Noah and
Faust, Aleksandra",
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.185/",
doi = "10.18653/v1/2023.findings-emnlp.185",
pages = "2803--2821",
abstract = "Large language models (LLMs) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding {--} i.e., parsing the raw HTML of a webpage, with applications to automation of web-based tasks, crawling, and browser-assisted retrieval {--} have not been fully explored. We contribute HTML understanding models (fine-tuned LLMs) and an in-depth analysis of their capabilities under three tasks: (i) Semantic Classification of HTML elements, (ii) Description Generation for HTML inputs, and (iii) Autonomous Web Navigation of HTML pages. While previous work has developed dedicated architectures and training procedures for HTML understanding, we show that LLMs pretrained on standard natural language corpora transfer remarkably well to HTML understanding tasks. For instance, when fine-tuned on data from the MiniWoB benchmark, LLMs successfully complete 50{\%} more tasks using 192x less data compared to the previous best supervised model. We create and open-source a large-scale HTML dataset distilled and auto-labeled from CommonCrawl"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gur-etal-2023-understanding">
<titleInfo>
<title>Understanding HTML with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Izzeddin</namePart>
<namePart type="family">Gur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ofir</namePart>
<namePart type="family">Nachum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingjie</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Safdari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Austin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Chowdhery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharan</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Fiedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Faust</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) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding – i.e., parsing the raw HTML of a webpage, with applications to automation of web-based tasks, crawling, and browser-assisted retrieval – have not been fully explored. We contribute HTML understanding models (fine-tuned LLMs) and an in-depth analysis of their capabilities under three tasks: (i) Semantic Classification of HTML elements, (ii) Description Generation for HTML inputs, and (iii) Autonomous Web Navigation of HTML pages. While previous work has developed dedicated architectures and training procedures for HTML understanding, we show that LLMs pretrained on standard natural language corpora transfer remarkably well to HTML understanding tasks. For instance, when fine-tuned on data from the MiniWoB benchmark, LLMs successfully complete 50% more tasks using 192x less data compared to the previous best supervised model. We create and open-source a large-scale HTML dataset distilled and auto-labeled from CommonCrawl</abstract>
<identifier type="citekey">gur-etal-2023-understanding</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.185</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.185/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>2803</start>
<end>2821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding HTML with Large Language Models
%A Gur, Izzeddin
%A Nachum, Ofir
%A Miao, Yingjie
%A Safdari, Mustafa
%A Huang, Austin
%A Chowdhery, Aakanksha
%A Narang, Sharan
%A Fiedel, Noah
%A Faust, Aleksandra
%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 gur-etal-2023-understanding
%X Large language models (LLMs) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding – i.e., parsing the raw HTML of a webpage, with applications to automation of web-based tasks, crawling, and browser-assisted retrieval – have not been fully explored. We contribute HTML understanding models (fine-tuned LLMs) and an in-depth analysis of their capabilities under three tasks: (i) Semantic Classification of HTML elements, (ii) Description Generation for HTML inputs, and (iii) Autonomous Web Navigation of HTML pages. While previous work has developed dedicated architectures and training procedures for HTML understanding, we show that LLMs pretrained on standard natural language corpora transfer remarkably well to HTML understanding tasks. For instance, when fine-tuned on data from the MiniWoB benchmark, LLMs successfully complete 50% more tasks using 192x less data compared to the previous best supervised model. We create and open-source a large-scale HTML dataset distilled and auto-labeled from CommonCrawl
%R 10.18653/v1/2023.findings-emnlp.185
%U https://aclanthology.org/2023.findings-emnlp.185/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.185
%P 2803-2821
Markdown (Informal)
[Understanding HTML with Large Language Models](https://aclanthology.org/2023.findings-emnlp.185/) (Gur et al., Findings 2023)
ACL
- Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel, and Aleksandra Faust. 2023. Understanding HTML with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2803–2821, Singapore. Association for Computational Linguistics.