ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Reza, Mohi, Laundry, Nathan, Musabirov, Ilya, Dushniku, Peter, Yu, Zhi Yuan "Michael", Mittal, Kashish, Grossman, Tovi, Liut, Michael, Kuzminykh, Anastasia, Williams, Joseph Jay
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911815280099328
author Reza, Mohi
Laundry, Nathan
Musabirov, Ilya
Dushniku, Peter
Yu, Zhi Yuan "Michael"
Mittal, Kashish
Grossman, Tovi
Liut, Michael
Kuzminykh, Anastasia
Williams, Joseph Jay
author_facet Reza, Mohi
Laundry, Nathan
Musabirov, Ilya
Dushniku, Peter
Yu, Zhi Yuan "Michael"
Mittal, Kashish
Grossman, Tovi
Liut, Michael
Kuzminykh, Anastasia
Williams, Joseph Jay
contents Exploring alternative ideas by rewriting text is integral to the writing process. State-of-the-art Large Language Models (LLMs) can simplify writing variation generation. However, current interfaces pose challenges for simultaneous consideration of multiple variations: creating new variations without overwriting text can be difficult, and pasting them sequentially can clutter documents, increasing workload and disrupting writers' flow. To tackle this, we present ABScribe, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks. With ABScribe, users can swiftly modify variations using LLM prompts, which are auto-converted into reusable buttons. Variations are stored adjacently within text fields for rapid in-place comparisons using mouse-over interactions on a popup toolbar. Our user study with 12 writers shows that ABScribe significantly reduces task workload (d = 1.20, p < 0.001), enhances user perceptions of the revision process (d = 2.41, p < 0.001) compared to a popular baseline workflow, and provides insights into how writers explore variations using LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2310_00117
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models
Reza, Mohi
Laundry, Nathan
Musabirov, Ilya
Dushniku, Peter
Yu, Zhi Yuan "Michael"
Mittal, Kashish
Grossman, Tovi
Liut, Michael
Kuzminykh, Anastasia
Williams, Joseph Jay
Human-Computer Interaction
Artificial Intelligence
Machine Learning
Exploring alternative ideas by rewriting text is integral to the writing process. State-of-the-art Large Language Models (LLMs) can simplify writing variation generation. However, current interfaces pose challenges for simultaneous consideration of multiple variations: creating new variations without overwriting text can be difficult, and pasting them sequentially can clutter documents, increasing workload and disrupting writers' flow. To tackle this, we present ABScribe, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks. With ABScribe, users can swiftly modify variations using LLM prompts, which are auto-converted into reusable buttons. Variations are stored adjacently within text fields for rapid in-place comparisons using mouse-over interactions on a popup toolbar. Our user study with 12 writers shows that ABScribe significantly reduces task workload (d = 1.20, p < 0.001), enhances user perceptions of the revision process (d = 2.41, p < 0.001) compared to a popular baseline workflow, and provides insights into how writers explore variations using LLMs.
title ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models
topic Human-Computer Interaction
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.00117