Can You Try Again?: Using Large Language Models to Generate Alt Text for Online Image Collections

Theresa Berger; Cody Hennesy; Jackson Myers

Can You Try Again?: Using Large Language Models to Generate Alt Text for Online Image Collections

Theresa Berger
, Cody Hennesy
, Jackson Myers

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

Abstract

We will detail findings from a 3-month project using LLMs’ (Large Language Models) to generate web-compliant alternative text (alt text) descriptions for born-digital and digitized still images. The presentation will highlight the platforms tested, building a chat assistant, workflows, successes, and failures.

Original language	English (US)
Title of host publication	2024 Virtual Digital Library Federation Forum
State	Published - Oct 2024

Find It

Find It at U of M Libraries

Cite this

@inproceedings{b851a8d94a104ecca57aa5821d5c2fb1,

title = "Can You Try Again?: Using Large Language Models to Generate Alt Text for Online Image Collections",

abstract = "We will detail findings from a 3-month project using LLMs{\textquoteright} (Large Language Models) to generate web-compliant alternative text (alt text) descriptions for born-digital and digitized still images. The presentation will highlight the platforms tested, building a chat assistant, workflows, successes, and failures.",

author = "Theresa Berger and Cody Hennesy and Jackson Myers",

year = "2024",

month = oct,

language = "English (US)",

booktitle = "2024 Virtual Digital Library Federation Forum",

}

TY - GEN

T1 - Can You Try Again?: Using Large Language Models to Generate Alt Text for Online Image Collections

AU - Berger, Theresa

AU - Hennesy, Cody

AU - Myers, Jackson

PY - 2024/10

Y1 - 2024/10

N2 - We will detail findings from a 3-month project using LLMs’ (Large Language Models) to generate web-compliant alternative text (alt text) descriptions for born-digital and digitized still images. The presentation will highlight the platforms tested, building a chat assistant, workflows, successes, and failures.

AB - We will detail findings from a 3-month project using LLMs’ (Large Language Models) to generate web-compliant alternative text (alt text) descriptions for born-digital and digitized still images. The presentation will highlight the platforms tested, building a chat assistant, workflows, successes, and failures.

UR - https://osf.io/pc4rx/

M3 - Conference contribution

BT - 2024 Virtual Digital Library Federation Forum

ER -

Can You Try Again?: Using Large Language Models to Generate Alt Text for Online Image Collections

Abstract

Find It

Other files and links

Fingerprint

Cite this