[2508.19227] Generative Interfaces for Language Models
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.
Generative Interfaces for Language Models Jiaqi Chen* †1 , Yanzhe Zhang* 2 , Yutong Zhang1 , Yijia Shao1 , Diyi Yang1 1 Stanford University 2 Georgia Tech chenjq24@stanford.edu, z_yanzhe@gatech.edu, diyiy@stanford.edu Abstract (LLMs) have…
saved by
related reading
- LLMs Get Lost in Evolving User Intentarxiv.org
- Group | Sherry Tongshuang Wucs.cmu.edu
- Simulating Users with State Alignment Beats Response Imitationhumanlm.stanford.edu
- Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantsarxiv.org
- user_interactions.pdfself-distillation.github.io
- Imagining better interfaces to language models | thesephist.comthesephist.com
- Why Chatbots Are Not the Future of Interfaceswattenberger.com
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- The case against conversational interfaces << julian.digitaljulian.digital
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io