HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model

Danai Vachtsevanou; Jérémy Lemée; Raffael Rot; Simon Mayer; Andrei Ciortea; Ganesh Ramanathan

doi:10.1145/3603163.3609077

HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model

Danai Vachtsevanou, Jérémy Lemée, Raffael Rot, Simon Mayer, Andrei Ciortea, Ganesh Ramanathan

University of St. Gallen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

We present HyperBrain, a hypermedia client that autonomously navigates hypermedia environments to achieve user goals specified in natural language. To achieve this, the client makes use of a large language model to decide which of the available hypermedia controls should be used within a given application context. In a demonstrative scenario, we show the client's ability to autonomously select and follow simple hyperlinks towards a high-level goal, successfully traversing the hypermedia structure of Wikipedia given only the markup of the respective resources. We show that hypermedia navigation based on language models is effective, and propose that this should be considered as a step to create hypermedia environments that are used by autonomous clients alongside people.

Original language	English
Title of host publication	Proceedings of the 34th ACM Conference on Hypertext and Social Media
Publisher	Association for Computing Machinery (ACM)
Pages	1-5
Number of pages	5
ISBN (Print)	9798400702327
DOIs	https://doi.org/10.1145/3603163.3609077
Publication status	Published - 5 Sept 2023
Externally published	Yes
Event	34th ACM Conference on Hypertext and Social Media - Rome, Italy Duration: 4 Sept 2023 → 8 Sept 2023 https://ht.acm.org/ht2023/hypertext-2023/

Conference

Conference	34th ACM Conference on Hypertext and Social Media
Abbreviated title	HT '23
Country/Territory	Italy
City	Rome
Period	4/09/23 → 8/09/23
Internet address	https://ht.acm.org/ht2023/hypertext-2023/

Access to Document

10.1145/3603163.3609077Licence: Unspecified

Cite this

@inproceedings{ab6d36fcf94548bcb29f2dc7036ed95c,

title = "HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model",

abstract = "We present HyperBrain, a hypermedia client that autonomously navigates hypermedia environments to achieve user goals specified in natural language. To achieve this, the client makes use of a large language model to decide which of the available hypermedia controls should be used within a given application context. In a demonstrative scenario, we show the client's ability to autonomously select and follow simple hyperlinks towards a high-level goal, successfully traversing the hypermedia structure of Wikipedia given only the markup of the respective resources. We show that hypermedia navigation based on language models is effective, and propose that this should be considered as a step to create hypermedia environments that are used by autonomous clients alongside people.",

keywords = "Hypermedia, Large Language Model, HATEOAS, Web of Things",

author = "Danai Vachtsevanou and J{\'e}r{\'e}my Lem{\'e}e and Raffael Rot and Simon Mayer and Andrei Ciortea and Ganesh Ramanathan",

year = "2023",

month = sep,

day = "5",

doi = "10.1145/3603163.3609077",

language = "English",

isbn = "9798400702327",

pages = "1--5",

booktitle = "Proceedings of the 34th ACM Conference on Hypertext and Social Media",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "34th ACM Conference on Hypertext and Social Media, HT '23 ; Conference date: 04-09-2023 Through 08-09-2023",

url = "https://ht.acm.org/ht2023/hypertext-2023/",

}

Vachtsevanou, D, Lemée, J, Rot, R, Mayer, S, Ciortea, A & Ramanathan, G 2023, HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model. in Proceedings of the 34th ACM Conference on Hypertext and Social Media., 3, Association for Computing Machinery (ACM), pp. 1-5, 34th ACM Conference on Hypertext and Social Media, Rome, Italy, 4/09/23. https://doi.org/10.1145/3603163.3609077

HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model. / Vachtsevanou, Danai; Lemée, Jérémy; Rot, Raffael et al.
Proceedings of the 34th ACM Conference on Hypertext and Social Media. Association for Computing Machinery (ACM), 2023. p. 1-5 3.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - HyperBrain

T2 - 34th ACM Conference on Hypertext and Social Media

AU - Vachtsevanou, Danai

AU - Lemée, Jérémy

AU - Rot, Raffael

AU - Mayer, Simon

AU - Ciortea, Andrei

AU - Ramanathan, Ganesh

PY - 2023/9/5

Y1 - 2023/9/5

N2 - We present HyperBrain, a hypermedia client that autonomously navigates hypermedia environments to achieve user goals specified in natural language. To achieve this, the client makes use of a large language model to decide which of the available hypermedia controls should be used within a given application context. In a demonstrative scenario, we show the client's ability to autonomously select and follow simple hyperlinks towards a high-level goal, successfully traversing the hypermedia structure of Wikipedia given only the markup of the respective resources. We show that hypermedia navigation based on language models is effective, and propose that this should be considered as a step to create hypermedia environments that are used by autonomous clients alongside people.

AB - We present HyperBrain, a hypermedia client that autonomously navigates hypermedia environments to achieve user goals specified in natural language. To achieve this, the client makes use of a large language model to decide which of the available hypermedia controls should be used within a given application context. In a demonstrative scenario, we show the client's ability to autonomously select and follow simple hyperlinks towards a high-level goal, successfully traversing the hypermedia structure of Wikipedia given only the markup of the respective resources. We show that hypermedia navigation based on language models is effective, and propose that this should be considered as a step to create hypermedia environments that are used by autonomous clients alongside people.

KW - Hypermedia

KW - Large Language Model

KW - HATEOAS

KW - Web of Things

UR - https://www.scopus.com/pages/publications/85174236592

UR - https://dl.acm.org/doi/proceedings/10.1145/3603163

U2 - 10.1145/3603163.3609077

DO - 10.1145/3603163.3609077

M3 - Conference contribution

SN - 9798400702327

SP - 1

EP - 5

BT - Proceedings of the 34th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery (ACM)

Y2 - 4 September 2023 through 8 September 2023

ER -

HyperBrain: Human-Inspired Hypermedia Guidance Using a Large Language Model

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this