From Words to Widgets for Controllable LLM Generation

TL;DR

Malleable Prompting is an interactive technique that transforms natural language preferences into GUI widgets, enabling precise and transparent control over large language model outputs.

Contribution

It introduces a novel method to reify subjective preferences into configurable GUI controls for improved LLM output steering.

Findings

Participants achieved target preferences more precisely with Malleable Prompting.

Users perceived the method as more controllable and transparent.

The approach visualizes control influence to support attribution and comparison.

Abstract

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.