Hierarchical Prompting Assists Large Language Model on Web Navigation
Abishek Sridhar, Robert Lo, Frank F. Xu, Hao Zhu, Shuyan Zhou
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.
BibTeX
@inproceedings{
sridhar2023hierarchical,
title={Hierarchical Prompting Assists Large Language Model on Web Navigation},
author={Abishek Sridhar and Robert Lo and Frank F. Xu and Hao Zhu and Shuyan Zhou},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=N3a2vVk8vu}
}