Large language model (LLM) powered chatbots are primarily text-based today, and impose a large interactional cognitive load, especially for exploratory or sensemaking tasks such as planning a trip or learning about a new city. Because the interaction is textual, users have little scaffolding in the way of structure, informational “scent”, or ability to specify high-level preferences or goals. We introduce ExploreLLM that allows users to structure thoughts, help explore different options, navigate through the choices and recommendations, and to more easily steer models to generate more personalized responses. We conduct a user study and show that users find it helpful to use ExploreLLM for exploratory or planning tasks, because it provides a useful schema-like structure to the task, and guides users in planning. The study also suggests that users can more easily personalize responses with high-level preferences with ExploreLLM.
@inproceedings{10.1145/3613905.3651093,
author = {Ma, Xiao and Mishra, Swaroop and Liu, Ariel and Su, Sophie Ying and Chen, Jilin and Kulkarni, Chinmay and Cheng, Heng-Tze and Le, Quoc and Chi, Ed},
title = {Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses},
year = {2024},
isbn = {9798400703317},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3613905.3651093},
doi = {10.1145/3613905.3651093},
booktitle = {Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
articleno = {56},
numpages = {12},
keywords = {Artificial Intelligence, Chatbots, Graphical User Interfaces, Interaction, Large Language Models, Learning from Instruction., Natural Language Interfaces, Prompting, Schema, Task Decomposition},
location = {, Honolulu , HI , USA , },
series = {CHI EA '24}
}