A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration

Abstract

With ChatGPT's release, conversational prompting has become the most popular form of human-LLM interaction. However, its effectiveness is limited for more complex tasks involving reasoning, creativity, and iteration. Through a systematic analysis of HCI papers published since 2021, we identified four key phases in the human-LLM interaction flow - planning, facilitating, iterating, and testing - to precisely understand the dynamics of this process. Additionally, we have developed a taxonomy of four primary interaction modes: Mode 1: Standard Prompting, Mode 2: User Interface, Mode 3: Context-based, and Mode 4: Agent Facilitator. This taxonomy was further enriched using the "5W1H" guideline method, which involved a detailed examination of definitions, participant roles (Who), the phases that happened (When), human objectives and LLM abilities (What), and the mechanics of each interaction mode (How). We anticipate this taxonomy will contribute to the future design and evaluation of human-LLM interaction.

11 pages, 4 figures, 3 tables. Accepted at CHI Late-Breaking Work 2024

References in corpus (14)

• CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities
• The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development
• Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding
• StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement
• "What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
• The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers
• Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
• Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting
• Spellburst: A Node-based Interface for Exploratory Creative Coding with Natural Language Prompts
• Competent but Rigid: Identifying the Gap in Empowering AI to Participate Equally in Group Decision-Making
• Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System
• ScatterShot: Interactive In-context Example Curation for Text Transformation
• GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks
• Developing a Conversational Recommendation System for Navigating Limited Options