Open-Set Living Need Prediction with Large Language Models

2025-06-03

AI Summary

Conventional life-need prediction relies on closed-set classification, failing to capture the open-endedness and fine-grained diversity of real-world human needs. Method: This work pioneers an open-set classification formulation for life-need prediction and introduces a novel LLM-based paradigm. It integrates behavior-aware retrieval with Maslow’s hierarchy of needs to design an interpretable, scalable digital need recall module, comprising a need-alignment mechanism, instruction tuning, and a lightweight text embedding model. Contribution/Results: Evaluated on real-world platform data, our approach achieves a 19.37% average improvement in service recall over closed-set baselines. Human evaluation confirms the reasonableness and specificity of predicted needs. The framework enables efficient deployment of small-scale LLMs, balancing practical applicability with theoretical innovation in open-set demand modeling.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Living needs are the needs people generate in their daily lives for survival and well-being. On life service platforms like Meituan, user purchases are driven by living needs, making accurate living need predictions crucial for personalized service recommendations. Traditional approaches treat this prediction as a closed-set classification problem, severely limiting their ability to capture the diversity and complexity of living needs. In this work, we redefine living need prediction as an open-set classification problem and propose PIGEON, a novel system leveraging large language models (LLMs) for unrestricted need prediction. PIGEON first employs a behavior-aware record retriever to help LLMs understand user preferences, then incorporates Maslow's hierarchy of needs to align predictions with human living needs. For evaluation and application, we design a recall module based on a fine-tuned text embedding model that links flexible need descriptions to appropriate life services. Extensive experiments on real-world datasets demonstrate that PIGEON significantly outperforms closed-set approaches on need-based life service recall by an average of 19.37%. Human evaluation validates the reasonableness and specificity of our predictions. Additionally, we employ instruction tuning to enable smaller LLMs to achieve competitive performance, supporting practical deployment.

Problem

• Predict diverse open-set living needs for personalized recommendations
• Leverage LLMs to overcome closed-set classification limitations
• Align predictions with human needs using Maslow's hierarchy

Innovation

• Open-set classification using large language models
• Behavior-aware record retriever for user preferences
• Maslow's hierarchy aligns predictions with needs