mlsanityData to 14 Oct 2026

DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls

arXiv 2610.04174 ↗First posted 3 Oct 2026cs.HC cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 3 Oct 2026.

Builds on

15 of 26 references.

References · 15

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  3. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  4. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  5. 2023Steering Language Models With Activation Engineeringcited by 922
  6. 2024Not All Language Model Features Are One-Dimensionally Linearcited by 212
  7. 2023Eliciting Human Preferences with Language Modelscited by 92
  8. 2023Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfacescited by 72
  9. 2023Challenges with unsupervised LLM knowledge discoverycited by 31
  10. 2024Supporting Sensemaking of Large Language Model Outputs at Scalecited by 27
  11. 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wildcited by 25
  12. 2026From Words to Widgets for Controllable LLM Generationcited by 5
3 more
  1. 2024Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Taskscited by 3
  2. 2025PromptCanvas: Composable Prompting Workspaces Using Dynamic Widgets for Exploration and Iteration in Creative Writingcited by 2
  3. 2026Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activationscited by 1

Built on by

Not cited yet.