Generative Interfaces for Language Models

TL;DR

This paper introduces generative interfaces for large language models that proactively create user interfaces to improve multi-turn, information-dense, and exploratory interactions, outperforming traditional chat-based systems.

Contribution

It proposes a new paradigm where LLMs generate adaptive UIs, along with a multidimensional evaluation framework demonstrating significant user preference improvements.

Findings

Generative interfaces outperform chat-based systems with up to 72% user preference improvement.

Structured representations and iterative refinement enhance UI generation quality.

Evaluation across diverse tasks shows consistent advantages of generative interfaces.

Abstract

Large language models (LLMs) are increasingly seen as assistants, copilots, and consultants, capable of supporting a wide range of tasks through natural conversation. However, most systems remain constrained by a linear request-response format that often makes interactions inefficient in multi-turn, information-dense, and exploratory tasks. To address these limitations, we propose Generative Interfaces for Language Models, a paradigm in which LLMs respond to user queries by proactively generating user interfaces (UIs) that enable more adaptive and interactive engagement. Our framework leverages structured interface-specific representations and iterative refinements to translate user queries into task-specific UIs. For systematic evaluation, we introduce a multidimensional assessment framework that compares generative interfaces with traditional chat-based ones across diverse tasks, interaction patterns, and query types, capturing functional, interactive, and emotional aspects of user experience. Results show that generative interfaces consistently outperform conversational ones, with up to a 72% improvement in human preference. These findings clarify when and why users favor generative interfaces, paving the way for future advancements in human-AI interaction. Data and code are available at https://github.com/SALT-NLP/GenUI.