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

arXiv:2310.00117v3 Announce Type: replace-cross
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 …

abstract art arxiv challenges cs.ai cs.hc cs.lg current exploration however human ideas integral interfaces language language models large language large language models llms multiple organization process state tasks text type variation writing