Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Map of Exploring Human Interaction patterns with LLM: Insights into Collaboration and Creativity

Jiayang Li, Jiale Li

TL;DR

This paper addresses the lack of focused mappings of human-LLM interaction by proposing a five-stage mapping procedure and applying it to 106 user-centered publications. By defining two analytical dimensions—Human-AI and Implement-Creation—and four AI roles, it clusters the literature into Processing Tool, Analysis Assistant, Creative Companion, and Processing Agent using manual scoring and K-means clustering. The resulting map clarifies how LLMs participate in collaboration and creativity, revealing a dominance of creative and autonomous roles and highlighting gaps such as explainability in mid-collaboration intervals. The methodology and resulting landscape provide a practical framework for evaluating current LLM-based systems and guiding future research in HAII patterns and AI-assisted creativity.

Abstract

The outstanding performance capabilities of large language model have driven the evolution of current AI system interaction patterns. This has led to considerable discussion within the Human-AI Interaction (HAII) community. Numerous studies explore this interaction from technical, design, and empirical perspectives. However, the majority of current literature reviews concentrate on interactions across the wider spectrum of AI, with limited attention given to the specific realm of interaction with LLM. We searched for articles on human interaction with LLM, selecting 110 relevant publications meeting consensus definition of Human-AI interaction. Subsequently, we developed a comprehensive Mapping Procedure, structured in five distinct stages, to systematically analyze and categorize the collected publications. Applying this methodical approach, we meticulously mapped the chosen studies, culminating in a detailed and insightful representation of the research landscape. Overall, our review presents an novel approach, introducing a distinctive mapping method, specifically tailored to evaluate human-LLM interaction patterns. We conducted a comprehensive analysis of the current research in related fields, employing clustering techniques for categorization, which enabled us to clearly delineate the status and challenges prevalent in each identified area.

A Map of Exploring Human Interaction patterns with LLM: Insights into Collaboration and Creativity

TL;DR

This paper addresses the lack of focused mappings of human-LLM interaction by proposing a five-stage mapping procedure and applying it to 106 user-centered publications. By defining two analytical dimensions—Human-AI and Implement-Creation—and four AI roles, it clusters the literature into Processing Tool, Analysis Assistant, Creative Companion, and Processing Agent using manual scoring and K-means clustering. The resulting map clarifies how LLMs participate in collaboration and creativity, revealing a dominance of creative and autonomous roles and highlighting gaps such as explainability in mid-collaboration intervals. The methodology and resulting landscape provide a practical framework for evaluating current LLM-based systems and guiding future research in HAII patterns and AI-assisted creativity.

Abstract

The outstanding performance capabilities of large language model have driven the evolution of current AI system interaction patterns. This has led to considerable discussion within the Human-AI Interaction (HAII) community. Numerous studies explore this interaction from technical, design, and empirical perspectives. However, the majority of current literature reviews concentrate on interactions across the wider spectrum of AI, with limited attention given to the specific realm of interaction with LLM. We searched for articles on human interaction with LLM, selecting 110 relevant publications meeting consensus definition of Human-AI interaction. Subsequently, we developed a comprehensive Mapping Procedure, structured in five distinct stages, to systematically analyze and categorize the collected publications. Applying this methodical approach, we meticulously mapped the chosen studies, culminating in a detailed and insightful representation of the research landscape. Overall, our review presents an novel approach, introducing a distinctive mapping method, specifically tailored to evaluate human-LLM interaction patterns. We conducted a comprehensive analysis of the current research in related fields, employing clustering techniques for categorization, which enabled us to clearly delineate the status and challenges prevalent in each identified area.
Paper Structure (27 sections, 7 figures)

This paper contains 27 sections, 7 figures.

Table of Contents

  1. Introduction
  2. Related work
  3. The Undergoing Change in HAII driven by large language model
  4. General Intelligence — The capability to process complex tasks and the ability for continual learning.
  5. Intention Understanding — Natural Language Based Interaction and Collaboration.
  6. Creativity — the ability to create new content.
  7. The Current Review of Human-AI Interaction
  8. Different understanding of A in HAII Review.
  9. Current Mapping of HAII
  10. Method
  11. Search and Selection
  12. Mapping
  13. Result
  14. Processing tool
  15. Analysis assistant
  16. ...and 12 more sections

Figures (7)

  • Figure 1: Flow diagram of the database searches and article screenings.
  • Figure 2: Types of task division between human and AI in work.
  • Figure 3: Innovation level of content produced through human-AI task.
  • Figure 4: The overall scores of the article in the map.
  • Figure 5: Elbow (left) and silhouette (right) method for determining the optimal number of clusters.
  • ...and 2 more figures