Understanding HTML with Large Language Models
Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin V Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel
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
BibTeX
@inproceedings{
gur2023understanding,
title={Understanding {HTML} with Large Language Models},
author={Izzeddin Gur and Ofir Nachum and Yingjie Miao and Mustafa Safdari and Austin V Huang and Aakanksha Chowdhery and Sharan Narang and Noah Fiedel and Aleksandra Faust},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=r65IWQmsHF}
}