Tuning Language Models for Robust Prediction of Diverse User Behaviors

• URL: http://arxiv.org/abs/2505.17682v1
• Date: Fri, 23 May 2025 09:53:43 GMT
• Title: Tuning Language Models for Robust Prediction of Diverse User Behaviors
• Authors: Fanjin Meng, Jingtao Ding, Jiahui Gong, Chen Yang, Hong Chen, Zuojian Wang, Haisheng Lu, Yong Li,
• Abstract summary: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behaviors.<n>We introduce BehaviorLM, a progressive fine-tuning approach that addresses this issue.<n> Experimental results on two real-world datasets demonstrate that BehaviorLM robustly predicts both anchor and tail behaviors.
• Score: 14.342911841456663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behaviors. Large language models (LLMs), with their pretraining on vast corpora containing rich behavioral knowledge, offer promise. However, existing fine-tuning approaches tend to overfit to frequent ``anchor'' behaviors, reducing their ability to predict less common ``tail'' behaviors. In this paper, we introduce BehaviorLM, a progressive fine-tuning approach that addresses this issue. In the first stage, LLMs are fine-tuned on anchor behaviors while preserving general behavioral knowledge. In the second stage, fine-tuning uses a balanced subset of all behaviors based on sample difficulty to improve tail behavior predictions without sacrificing anchor performance. Experimental results on two real-world datasets demonstrate that BehaviorLM robustly predicts both anchor and tail behaviors and effectively leverages LLM behavioral knowledge to master tail behavior prediction with few-shot examples.

Related papers

• Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes [35.431529010502835]
  SmartGen is a framework that synthesizes context-aware user behavior data to support continual adaptation of downstream smart home models.<n>SmartGen significantly enhances model performance on anomaly detection and behavior prediction tasks under behavioral drift.
  arXiv  Detail & Related papers  (2025-08-05T14:16:10Z)
• Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning [27.226155951073064]
  Shop-R1 is a novel reinforcement learning framework aimed at enhancing the reasoning ability of Large Language Models (LLMs)<n>For rationale generation, we leverage internal model signals (e.g., logit distributions) to guide the reasoning process in a self-supervised manner.<n>For action prediction, we propose a hierarchical reward structure with difficulty-aware scaling to prevent reward hacking.
  arXiv  Detail & Related papers  (2025-07-23T18:10:43Z)
• Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm [57.00627691433355]
  We frame agent behavior steering as a model editing task, which we term Behavior Editing.<n>We introduce BehaviorBench, a benchmark grounded in psychological moral theories.<n>We demonstrate that Behavior Editing can be used to promote ethical and benevolent behavior or, conversely, to induce harmful or malicious behavior.
  arXiv  Detail & Related papers  (2025-06-25T16:51:51Z)
• BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling [14.342911841456663]
  We propose BehaveGPT, a foundational model designed specifically for large-scale user behavior prediction.<n>BehaveGPT is trained on vast user behavior datasets, allowing it to learn complex behavior patterns.<n>Our approach introduces the DRO-based pretraining paradigm tailored for user behavior data, which improves model generalization and transferability.
  arXiv  Detail & Related papers  (2025-05-23T08:43:46Z)
• Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training [60.38082979765664]
  CPRec is an All-domain Continual Pre-Training framework for Recommendation.<n>It holistically align LLMs with universal user behaviors through the continual pre-training paradigm.<n>We conduct experiments on five real-world datasets from two distinct platforms.
  arXiv  Detail & Related papers  (2025-04-11T20:01:25Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation [47.29682938439268]
  We propose a novel Counterfactual Fine-Tuning (CFT) method to improve user preference modeling. We employ counterfactual reasoning to identify the causal effects of behavior sequences on model output. Experiments on real-world datasets demonstrate that CFT effectively improves behavior sequence modeling.
  arXiv  Detail & Related papers  (2024-10-30T08:41:13Z)
• Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation [69.60321475454843]
  We propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. In the pre-training stage, we propose a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module.
  arXiv  Detail & Related papers  (2024-08-21T06:48:38Z)
• Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes via Loss-guided Mask [27.955323209766153]
  We propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference.
  arXiv  Detail & Related papers  (2024-06-16T13:23:21Z)
• Augmenting Interpretable Models with LLMs during Training [73.40079895413861]
  We propose Augmented Interpretable Models (Aug-imodels) to build efficient and interpretable models. Aug-imodels use LLMs during fitting but not during inference, allowing complete transparency. We explore two instantiations of Aug-imodels in natural-language processing: (i) Aug-GAM, which augments a generalized additive model with decoupled embeddings from an LLM and (ii) Aug-Tree, which augments a decision tree with LLM feature expansions.
  arXiv  Detail & Related papers  (2022-09-23T18:36:01Z)
• Recommender Transformers with Behavior Pathways [50.842316273120744]
  We build the Recommender Transformer (RETR) with a novel Pathway Attention mechanism. We empirically verify the effectiveness of RETR on seven real-world datasets.
  arXiv  Detail & Related papers  (2022-06-13T08:58:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.