@inproceedings{yang-etal-2026-sessionintentbench,
    title = "{S}ession{I}ntent{B}ench: A Multi-task Inter-session Intention-shift Modeling Benchmark for {E}-commerce Customer Behavior Understanding",
    author = "Yang, Yuqi  and
      Wang, Weiqi  and
      Xu, Baixuan  and
      Fan, Wei  and
      Zong, Qing  and
      Chan, Chunkit  and
      Deng, Zheye  and
      Liu, Xin  and
      Gao, Yifan  and
      Yu, Changlong  and
      Luo, Chen  and
      Li, Yang  and
      Li, Zheng  and
      Yin, Qingyu  and
      Yin, Bing  and
      Song, Yangqiu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.826/",
    pages = "16748--16775",
    ISBN = "979-8-89176-395-1",
    abstract = "Session history is a common way of recording user interacting behaviors throughout a browsing activity with multiple products. For example, if an user clicks a product webpage and then leaves, it might because there are certain features that don{'}t satisfy the user, which serve as an important indicator of on-the-spot user preferences. However, all prior works fail to capture and model customer intention effectively because insufficient information exploitation and only apparent information like descriptions and titles are used. There is also a lack of data and corresponding benchmark for explicitly modeling intention in E-commerce product purchase sessions. To address these issues, we introduce the concept of an intention tree and propose a dataset curation pipeline. Together, we construct a sibling multimodal benchmark, SessionIntentBench, that evaluates L(V)LMs' capability on understanding inter-session intention shift with four subtasks. With 1,952,177 intention entries, 1,132,145 session intention trajectories, and 13,003,664 available tasks mined using 10,905 sessions, we provide a scalable way to exploit the existing session data for customer intention understanding. We conduct human annotations to collect ground-truth label for a subset of collected data to form an evaluation gold set. Extensive experiments on the annotated data further confirm that current L(V)LMs fail to capture and utilize the intention across the complex session setting. Further analysis show injecting intention enhances LLMs' performances."
}