LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation

TL;DR

This paper introduces BUA, a framework that leverages large language models for human behavior prediction and generation by aligning behavioral data with language understanding through curriculum learning.

Contribution

The paper presents a novel curriculum learning approach that integrates LLMs into behavior modeling, addressing challenges like long-tail behaviors and multi-task support.

Findings

BUA outperforms existing methods on real-world datasets.

The framework enhances interpretability and task flexibility in behavior modeling.

Experiments demonstrate significant improvements in prediction and generation tasks.

Abstract

Human daily behavior unfolds as complex sequences shaped by intentions, preferences, and context. Effectively modeling these behaviors is crucial for intelligent systems such as personal assistants and recommendation engines. While recent advances in deep learning and behavior pre-training have improved behavior prediction, key challenges remain--particularly in handling long-tail behaviors, enhancing interpretability, and supporting multiple tasks within a unified framework. Large language models (LLMs) offer a promising direction due to their semantic richness, strong interpretability, and generative capabilities. However, the structural and modal differences between behavioral data and natural language limit the direct applicability of LLMs. To address this gap, we propose Behavior Understanding Alignment (BUA), a novel framework that integrates LLMs into human behavior modeling through a structured curriculum learning process. BUA employs sequence embeddings from pretrained behavior models as alignment anchors and guides the LLM through a three-stage curriculum, while a multi-round dialogue setting introduces prediction and generation capabilities. Experiments on two real-world datasets demonstrate that BUA significantly outperforms existing methods in both tasks, highlighting its effectiveness and flexibility in applying LLMs to complex human behavior modeling.