From Words to Widgets for Controllable LLM Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915933938778112 |
|---|---|
| author | Zhang, Chao Liu, Yiren Nie, Lunyiu Rzeszotarski, Jeffrey M. Huang, Yun August, Tal |
| author_facet | Zhang, Chao Liu, Yiren Nie, Lunyiu Rzeszotarski, Jeffrey M. Huang, Yun August, Tal |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10925 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Words to Widgets for Controllable LLM Generation Zhang, Chao Liu, Yiren Nie, Lunyiu Rzeszotarski, Jeffrey M. Huang, Yun August, Tal Human-Computer Interaction 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. |
| title | From Words to Widgets for Controllable LLM Generation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.10925 |