DimSteer helps writers control AI outputs with intuitive style sliders
DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls
Human-Computer InteractionComputation and Language
Summary
When using AI to write, it can be hard to get the style just right by typing instructions alone. The authors created DimSteer, a tool that shows users different writing versions and finds key style directions automatically. Users can then adjust these styles easily with sliders instead of retyping prompts. This method reduces the effort and frustration of editing while still letting users explore new writing styles.
What this means in practice
- •For content creators: Adjust AI-generated text styles quickly with sliders to improve writing efficiency and creativity.
- •For customer support teams: Fine-tune automated response tones using interactive controls to better match brand voice without rewriting prompts.
- •For marketing teams: Create tailored marketing copy by exploring stylistic variations through direct manipulation sliders for diverse campaigns.$Commercial implications: Supports building user-friendly AI writing assistants that offer style customization sliders to marketing professionals, enhancing campaign personalization.
Authors
Ajit Mallavarapu, Ziwei Gu
Abstract
Large language model writing interfaces often make users steer outputs by repeatedly articulating desired changes in natural language. Yet writers may recognize useful stylistic directions only after seeing alternatives, making revision recall-heavy. We present DimSteer, an authoring interface that samples prompt-local completions, discovers high-variance activation-space axes of variation, labels them, and exposes them as sliders with pole previews, diff comparison, and reset controls. Users can manipulate discovered dimensions, reducing the need to reformulate prompts for each stylistic adjustment. In a within-subjects study with 16 participants against a matched prompt-only baseline, DimSteer reduced mental demand, effort, and frustration while preserving comparable perceived success. Participants valued the surfaced dimensions, yet 15 of 16 disagreed that they would have thought to request the same changes in a prompt. Results suggest prompt-local controls can shift LLM authoring from recall-based prompting toward recognition-based exploration and direct manipulation, while preserving prompting for open-ended edits.