Supporting Effective Goal Setting with LLM-Based Chatbots

2026-02-09

AI Summary

This study addresses the challenge individuals face in effectively applying psychological frameworks when setting behavioral goals due to a lack of structured support. To bridge this gap, the authors propose a large language model (LLM)-based conversational system that integrates established theories—such as goal setting and implementation intentions—through three interaction mechanisms: guided prompting, adaptive suggestions, and feedback. In a preregistered randomized controlled trial with 543 participants, the study provides the first systematic evaluation of embedding psychological frameworks into an LLM-powered chatbot. Results demonstrate that the feedback mechanism significantly enhances goal quality, whereas the impact of adaptive suggestions is limited. These findings offer a scalable technical pathway for proactive behavioral interventions grounded in evidence-based psychological principles.

Technology Category

Cognitive Modeling & Cognitive Systems: Adaptive BehaviorData Mining & Knowledge Management: Conversational Systems for Recommendation & RetrievalMachine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

Each day, individuals set behavioral goals such as eating healthier, exercising regularly, or increasing productivity. While psychological frameworks (i.e., goal setting and implementation intentions) can be helpful, they often need structured external support, which interactive technologies can provide. We thus explored how large language model (LLM)-based chatbots can apply these frameworks to guide users in setting more effective goals. We conducted a preregistered randomized controlled experiment ($N = 543$) comparing chatbots with different combinations of three design features: guidance, suggestions, and feedback. We evaluated goal quality using subjective and objective measures. We found that, while guidance is already helpful, it is the addition of feedback that makes LLM-based chatbots effective in supporting participants'goal setting. In contrast, adaptive suggestions were less effective. Altogether, our study shows how to design chatbots by operationalizing psychological frameworks to provide effective support for reaching behavioral goals.

Problem

• goal setting
• LLM-based chatbots
• behavioral goals
• implementation intentions
• interactive technologies

Innovation

• LLM-based chatbots
• goal setting
• feedback mechanism
• randomized controlled trial
• behavioral goals