@inproceedings{wei-etal-2026-past,
    title = "From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation",
    author = "Wei, Kaiwen  and
      he, Kejun  and
      Kang, Xiaomian  and
      Zhang, Jie  and
      Ymyang  and
      Jin, Li  and
      Li, Zhenyang  and
      Zhong, Jiang  and
      Bai, Richard He  and
      Zhu, Junnan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.475/",
    pages = "10421--10441",
    ISBN = "979-8-89176-390-6",
    abstract = "Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, this left-to-right paradigm inherently biases the model towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.To address this limitation, we propose Masked History Learning (MHL), a novel training framework that shifts the objective from simple next-step prediction to deep comprehension of history. MHL augments the standard autoregressive objective with an auxiliary task of reconstructing masked historical items, compelling the model to understand ``why'' an item path is formed from the user{'}s past behaviors, rather than just ``what'' item comes next.We introduce two key contributions to enhance this framework: (1) an entropy-guided masking policy that intelligently targets the most informative historical items for reconstruction, and (2) a curriculum learning scheduler that progressively transitions from history reconstruction to future prediction.Experiments on three public datasets show that our method significantly outperforms state-of-the-art generative models, highlighting that a comprehensive understanding of the past is crucial for accurately predicting a user{'}s future path. The code is available at https://github.com/CQU-MM-Intelligent-Lab/MHL."
}