Abstract
Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation. However, their effectiveness in supporting domain-specific writing, particularly in business contexts, is relatively less explored. Our formative study with industry professionals revealed the limitations in current LLMs' understanding of the nuances in such domain-specific writing. To address this gap, we propose an approach of human-AI collaborative taxonomy development to perform as a guideline for domain-specific writing assistants. This method integrates iterative feedback from domain experts and multiple interactions between these experts and LLMs to refine the taxonomy. Through larger-scale experiments, we aim to validate this methodology and thus improve LLM-powered writing assistance, tailoring it to meet the unique requirements of different stakeholder needs.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the 3rd Workshop on Intelligent and Interactive Writing Assistants, In2Writing 2024, co-located with the ACM CHI Conference on Human Factors in Computing Systems, CHI 2024 |
Publisher | Association for Computing Machinery |
Pages | 51-57 |
Number of pages | 7 |
ISBN (Electronic) | 9798400710315 |
DOIs | |
State | Published - Oct 15 2024 |
Event | 3rd Workshop on Intelligent and Interactive Writing Assistants, In2Writing 2024, co-located with the ACM CHI Conference on Human Factors in Computing Systems, CHI 2024 - Honolulu, United States Duration: May 11 2024 → May 16 2024 |
Publication series
Name | ACM International Conference Proceeding Series |
---|
Conference
Conference | 3rd Workshop on Intelligent and Interactive Writing Assistants, In2Writing 2024, co-located with the ACM CHI Conference on Human Factors in Computing Systems, CHI 2024 |
---|---|
Country/Territory | United States |
City | Honolulu |
Period | 5/11/24 → 5/16/24 |
Bibliographical note
Publisher Copyright:© 2024 ACM.
Keywords
- AI-assisted Writing
- Human-AI Collaboration
- Taxonomy