Beyond Tools: Understanding How Heavy Users Integrate LLMs into Everyday Tasks and Decision-Making

2025-02-21

AI Summary

This study investigates how heavy users deeply integrate large language models (LLMs) into daily decision-making and cognitive practices—particularly in intuitive and analytical tasks—where LLMs assume non-instrumental roles such as social validation, self-regulation, and interpersonal guidance. Drawing on thematic analysis of in-depth interviews with seven heavy users, grounded in HCI and cognitive psychology theory, the work identifies a novel “cognitive co-ordination” integration paradigm, wherein users treat LLMs as “rational agents” or “average humans” rather than mere task-execution tools. Three high-level usage patterns emerge, directly challenging the instrumentalist assumption underlying mainstream LLM design. The findings provide both theoretical foundations and actionable design principles for human-centered AI systems that support cognitive augmentation and socially embedded interaction.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large language models (LLMs) are increasingly used for both everyday and specialized tasks. While HCI research focuses on domain-specific applications, little is known about how heavy users integrate LLMs into everyday decision-making. Through qualitative interviews with heavy LLM users (n=7) who employ these systems for both intuitive and analytical thinking tasks, our findings show that participants use LLMs for social validation, self-regulation, and interpersonal guidance, seeking to build self-confidence and optimize cognitive resources. These users viewed LLMs either as rational, consistent entities or average human decision-makers. Our findings suggest that heavy LLM users develop nuanced interaction patterns beyond simple delegation, highlighting the need to reconsider how we study LLM integration in decision-making processes.

Problem

• LLM integration in daily tasks
• Heavy users' decision-making patterns
• Nuanced LLM interaction beyond delegation

Innovation

• LLMs for social validation
• LLMs enhance self-regulation
• LLMs provide interpersonal guidance