SYNthia: An Interface Concept for Writing With Large Language Models

Abstract

Artificial intelligence (AI)-infused systems can offer valuable assistance to writers, but they may also produce imperfect or unsatisfactory suggestions that require efficient correction. Word choice presents a challenge for writers that can be addressed by several tools, but these systems typically require users to switch browser tabs or tools and break their flow of thinking, or otherwise fail to incorporate the context associated with users' writing or their intentions, leaving them with subpar or unrelated suggestions. We present SYNthia, a word-suggestion interface that allows users to be directly involved in the suggestion generation process by providing natural language feedback. We performed two pilot qualitative studies, finding that SYNthia provided users with a more practical interface that (1) allowed them to receive their target word more efficiently, (2) eliminated the need to for users switch contexts (e.g. switching tabs or devices), and (3) improved users' perceived quality of writing. In addition, we performed a formal user study comparing how novice and expert writers interact with SYNthia different, ultimately concluding that the writing level had no quantitatively significant impact on interactions with the tool, raising more questions for further study. However, the qualitative study surfaced several interesting observations regarding how writers interact with an AI-powered thesaurus, making progress towards the greater goal of integrating AI in the writing process while maintaining human agency and ownership. All code for this project can be found at the Github repository: https://github.com/AEst2002/word-suggester/tree/thesis.