Tue Oct 11 2022
Mon Oct 10 2022

Understanding HTML with Large Language Models

Artificial Intelligence
Natural Language Processing, Web Automation
Automation of web-based tasks, crawling, and browser-assisted retrieval

Explores the capabilities of large language models (LLMs) for HTML understanding and contributes HTML understanding models and an in-depth analysis of their capabilities under three tasks.

LLMs pretrained on standard natural language corpora transfer remarkably well to HTML understanding tasks, creating and open-sourcing a large-scale HTML dataset distilled and auto-labeled from CommonCrawl can promote further research on LLMs for HTML understanding.

In-Context Policy Iteration

Artificial Intelligence
Reinforcement Learning, Deep Learning
RL tasks in low-resource settings

Presents In-Context Policy Iteration (ICPI), an algorithm for performing Reinforcement Learning (RL) in-context, using foundation models without expert demonstrations or gradients

ICPI is a promising algorithm for RL tasks in low-resource settings, eliminating the role of in-weights learning, which can be slow and sacrificing the "few-shot" quality of in-context learning.

Wed Oct 05 2022
Mon Oct 03 2022
Fri Sep 30 2022
Sun Sep 25 2022