Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mohi Reza, Nathan Laundry, Ilya Musabirov, Peter Dushniku, Zhi Yuan "Michael" Yu, Kashish Mittal, Tovi Grossman, Michael Liut, Anastasia Kuzminykh, Joseph Jay Williams

TL;DR

ABScribe is presented, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks, and provides insights into how writers explore variations using LLMs.

Abstract

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.

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

TL;DR

ABScribe is presented, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks, and provides insights into how writers explore variations using LLMs.

Abstract

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.
Paper Structure (29 sections, 8 figures, 1 table)

This paper contains 29 sections, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Exploring Multiple Variations
  4. Working with Multiple Variations from Large Language Models
  5. Chat-Based and In-Place Human-AI Co-Writing Interfaces
  6. Designing ABScribe
  7. Design Requirements
  8. Interface Elements
  9. Design Process
  10. Variation Fields
  11. Popup Toolbar
  12. Variation Sidebar
  13. AI Modifiers
  14. AI Drafter
  15. Evaluating ABScribe
  16. ...and 14 more sections

Figures (8)

  • Figure 1: Variation Fields & Popup Toolbar: Users can choose, clone and edit multiple variations stored inside flexible text fields.
  • Figure 2: Variation Sidebar: Users can select, view, and navigate through multiple variations using an alternative accordion structure.
  • Figure 3: AI Modifiers: Variation Fields can also be edited using the AI Modifiers, which let users specify custom alterations. Descriptive labels are automatically generated for each AI Modifier to turn them into reusable buttons.
  • Figure 4: AI Drafter: Users can draft LLM-generated text directly into the document, providing tighter integration between the Human and AI generated writing workflow. Users can see the AI generated content in real-time and choose to insert or delete the output, or revise the prompt, giving them control over what is included in their document.
  • Figure 5: Overall results on NASA TLX subjective task workload
  • ...and 3 more figures