mlsanityData to 14 Oct 2026

From Words to Widgets for Controllable LLM Generation

arXiv 2604.10925 ↗First posted 13 Apr 2026cs.HC cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceived as more controllable and transparent than natural language prompting alone.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 33 of its 83 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

33 of 83 references.

References · 33

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  3. 2019The many Shapley values for model explanationcited by 344
  4. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 268
  5. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  6. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  7. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 94
  8. 2023Eliciting Human Preferences with Language Modelscited by 92
  9. 2024Aligning to Thousands of Preferences via System Message Generalizationcited by 84
  10. 2023EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteriacited by 74
  11. 2023Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfacescited by 72
  12. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
21 more
  1. 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinementcited by 62
  2. 2023PromptMagician: Interactive Prompt Engineering for Text-to-Image Creationcited by 58
  3. 2023VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototypingcited by 46
  4. 2025Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworkscited by 38
  5. 2024Supporting Sensemaking of Large Language Model Outputs at Scalecited by 27
  6. 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wildcited by 25
  7. 2024Context Steering: Controllable Personalization at Inference Timecited by 22
  8. 2025CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactionscited by 22
  9. 2024Know Your Audience: The benefits and pitfalls of generating plain language summaries beyond the "general" audiencecited by 13
  10. 2020InChorus: Designing Consistent Multimodal Interactions for Data Visualization on Tablet Devicescited by 12
  11. 2024Contextualized Evaluations: Judging Language Model Responses to Underspecified Queriescited by 12
  12. 2023Prompt Middleware: Mapping Prompts for Large Language Models to UI Affordancescited by 7
  13. 2024Beyond Content Relevance: Evaluating Instruction Following in Retrieval Modelscited by 6
  14. 2025Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflowscited by 6
  15. 2026Narrix: Remixing Narrative Strategies from Examples for Story Writingcited by 4
  16. 2025Composable Prompting Workspaces for Creative Writing: Exploration and Iteration Using Dynamic Widgetscited by 3
  17. 2025PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generationcited by 3
  18. 2025Show or Tell? Modeling the evolution of request-making in Human-LLM conversationscited by 3
  19. 2026Preference-Guided Prompt Optimization for Text-to-Image Generationcited by 2
  20. 2026Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMscited by 1
  21. 2026Interrogating Design Homogenization in Web Vibe Codingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wildcited by 1
  2. 2026Narrative Keyframing for Generative Creative Writingcited by 1
  3. 2026Designing Proactive Thought Partners for Writingcited by 1
  4. 2026Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responsescited by 0
  5. 2026DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controlscited by 0