Writing Assistants Should Model Social Factors of Language
This is a position paper proposing a new direction for writing assistants to address adoption barriers, but it is incremental as it builds on existing LLM technology without presenting new results.
The authors argue that writing assistants underperform because they focus only on information content and ignore social factors, proposing that incorporating these factors would improve effectiveness and user adoption.
Intelligent writing assistants powered by large language models (LLMs) are more popular today than ever before, but their further widespread adoption is precluded by sub-optimal performance. In this position paper, we argue that a major reason for this sub-optimal performance and adoption is a singular focus on the information content of language while ignoring its social aspects. We analyze the different dimensions of these social factors in the context of writing assistants and propose their incorporation into building smarter, more effective, and truly personalized writing assistants that would enrich the user experience and contribute to increased user adoption.