Behavior Understanding Alignment (BUA) Framework

Paper context

Paper title: LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation 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. Passages referencing this figure: stic dynamics without fixed rules, though its static generation parameters limit adaptability. More recently, D2A (Wang et al. , 2024 ) trained an LLM as a cognitively inspired agent guided by a dynamic value system, enhancing behavioral diversity and flexibility. However, it underutilizes the LLM’s potential for sequence generation based on a deep, multimodal understanding of behavioral context. Figure 1: The framework of Behavior Understanding Alignment (BUA). (a) the modality conversion process using sequence embedding. (b) curriculum for Behavior Understanding Alignment: seq-fea, user-fea, and refined-fea represent features learned in Stage 1 (Sequence-Level), Stage 2 (User-Level), and Stage 3 (Self-Reflection). The ✓ \checkmark and × \times marks indicate the correctness of the learne the model is tasked with either (1) predicting the next behavior b ∈ ℬ b\in\mathcal{B} , or (2) generating a future sequence Y seq = { y 1 , y 2 , … , y L 2 } Y_{\text{seq}}=\{y_{1},y_{2},\dots,y_{L_{2}}\} , where each y i y_{i} is a four-tuple ( d i , t i , l i , b i ) (d_{i},t_{i},l_{i},b_{i}) . 3.2 Overview The framework of our method, Behavior Understanding Alignment (BUA), is illustrated in Figure 1 . To effectively bridge the gap between numerical behavior data and textual semantic space, we first introduce a Sequence Embedding Alignment module, as detailed in Figure 1 (a). Given a user behavior sequence X seq X_{\text{seq}} , we utilize behaveGPT (Gong et al. , 2025 ) , a model pretrained on large-scale behavioral data, as the behavior encoder g ϕ g_{\phi} . The penultimate hidden =\{y_{1},y_{2},\dots,y_{L_{2}}\} , where each y i y_{i} is a four-tuple ( d i , t i , l i , b i ) (d_{i},t_{i},l_{i},b_{i}) . 3.2 Overview The framework of our method, Behavior Understanding Alignment