Elamur Research⌕
☰
home / papers / 2026 / SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding

Paper · 2026 · Yuqi Yang, Weiqi Wang, Baixuan Xu et al.

Summary

E-commerce services benefit from knowing what a shopper wants at a given moment. User profiles and purchase records are often missing, and earlier intention research covers only single or co-buy purchases, mostly using product titles and images. This paper models how preferences change step by step during a browsing session. The authors introduce an "intention tree" and an automated pipeline that prompts L(V)LMs in several stages. The pipeline enriches Amazon-M2 sessions with product metadata, valued attributes, inferred intentions and comparisons between consecutive items. The result is SessionIntentBench, a multimodal benchmark with four subtasks:

  • scoring purchase likelihood from a stated intention,
  • scoring likelihood under an assumed valued attribute,
  • judging whether a comparison justifies an intent shift,
  • deciding between exploitation and exploration for later recommendations.

A human-annotated gold subset is used for evaluation. More than 20 L(V)LMs were tested, and they perform poorly, especially at using intent to infer the next item and at tracking long-range shifts. Injecting intention knowledge from an external resource improves results. The work shows how existing session logs can be reused at scale for customer-intent research.

Key points

  • The data comes from 10,905 Amazon-M2 sessions that have full text and image information. They yield 1,952,177 intention entries, 1,132,145 intention trajectories and 13,003,664 candidate tasks.
  • The gold evaluation set contains 8,980 sampled trajectories, labelled by Amazon Mechanical Turk workers. Tasks 1–3 use a 0–3 ordinal scale, and Task 4 is a three-way choice.
  • The intention tree is generated with GPT-4o-mini, so generator bias is acknowledged as a limitation. Code and data are to be released under MIT.
  • Fine-tuning on SIB alone does not reliably help. For Llama-3.1-8B, Task 1 accuracy drops from 56.87% to 52.82% with SIB-only fine-tuning, but rises to 60.10% with sequential MIND + SIB fine-tuning.
  • The authors analysed 200 errors from GPT-4o with Chain-of-Thought. The most frequent cause (47.5%) is misuse of the provided metadata, particularly ignoring earlier session context.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Hong Kong University of Science and TechnologyHong Kong · China170 works · 26,341 citations🏢AmazonSeattle · United States128 works · 41,697 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksInformation Systems · 1,730 works

🧭 Topics 1Research subjects and languages the work is about.Evaluation & benchmarks · 1,341 works

Cite

Cite as Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin and Yangqiu Song. 2026. SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.826

@inproceedings{yang2026sessionintentbench,
  title = {{SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding}},
  author = {Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin and Yangqiu Song},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.826},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.826}
}

References

40 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bruce L Alford and Abhijit Biswas. 2002. The effects of discount level, price consciousness and sale proneness on consumers’ price perception and behavioral intention. Journal of Business Research, 55(9):775– 783. find
  2. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, Daniele Mazzotta, Badreddine Noune, Baptiste Pannier, and Guilherme Penedo. 2023. The falcon series of open language mo…
  3. Miguel Alves Gomes, Richard Meyes, Philipp Meisen, and Tobias Meisen. 2022. Will this online shopping session succeed? predicting customer’s purchase intention using embeddings. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, CIKM ’22, page 2873–2882, N… find
  4. Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, and Yangqiu Song. 2026. Intention knowledge graph construction for user intention relation modeling. In Proceedings of the 19th Conference of the European Chapter of the Association for Com… find
  5. Diddigi Raghu Ram Bharadwaj, Lakshya Kumar, Saif Jawaid, and Sreekanth Vempati. 2022. Fine-grained session recommendations in e-commerce using deep reinforcement learning. Preprint, arXiv:2210.15451. — [arXiv:2210.15451](https://arxiv.org/abs/2210.15451) find
  6. Minjin Choi, Hye-young Kim, Hyunsouk Cho, and Jongwuk Lee. 2024. Multi-intent-aware session-based recommendation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 2532–2536, New York, NY, USA. Association for Computin… find
  7. Honghua (Kathy) Dai, Lingzhi Zhao, Zaiqing Nie, Ji-Rong Wen, Lee Wang, and Ying Li. 2006. Detecting online commercial intention (oci). In Proceedings of the 15th International Conference on World Wide Web, WWW ’06, page 829–837, New York, NY, USA. Association for Computing Machinery. find
  8. Wenxuan Ding, Weiqi Wang, Sze Heng Douglas Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Junxian He, and Yangqiu Song. 2024. IntentionQA: A benchmark for evaluating purchase intention comprehension abilities of language models in E-com… find
  9. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… — The Llama 3 Herd of Models
  10. Yupeng Hou, Jiacheng Li, Zhankui He, An Yan, Xiusi Chen, and Julian McAuley. 2024. Bridging language and items for retrieval and recommendation. Preprint, arXiv:2403.03952. — [arXiv:2403.03952](https://arxiv.org/abs/2403.03952) find
  11. Derek Hao Hu, Qiang Yang, and Ying Li. 2008. An algorithm for analyzing personalized online commercial intention. In Proceedings of the 2nd International Workshop on Data Mining and Audience Intelligence for Advertising, ADKDD ’08, page 27–36, New York, NY, USA. Association for Computing Machinery. find
  12. Ravi Chandra Jammalamadaka, Naren Chittar, and Sanjay Ghatare. 2009. Mining product intention rules from transaction logs of an ecommerce portal. In Proceedings of the 2009 International Database Engineering & Applications Symposium, IDEAS ’09, page 311–314, New York, NY, USA. Association for Comput… find
  13. Bohan Jia, Jian Cao, Shiyou Qian, Nengjun Zhu, Xin Dong, Liang Zhang, Lei Cheng, and Linjian Mo. 2023. Smone: A session-based recommendation model based on neighbor sessions with similar probabilistic intentions. ACM Trans. Knowl. Discov. Data, 17(8). find
  14. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  15. Di Jin, Luzhi Wang, Yizhen Zheng, Guojie Song, Fei Jiang, Xiang Li, Wei Lin, and Shirui Pan. 2023a. Dual intent enhanced graph neural network for session-based new item recommendation. In Proceedings of the ACM Web Conference 2023, WWW ’23, page 684–693, New York, NY, USA. Association for Computing… find
  16. Wei Jin, Haitao Mao, Zheng Li, Haoming Jiang, Chen Luo, Hongzhi Wen, Haoyu Han, Hanqing Lu, Zhengyang Wang, Ruirui Li, Zhen Li, Monica Xiao Cheng, Rahul Goutam, Haiyang Zhang, Karthik Subbian, Suhang Wang, Yizhou Sun, Jiliang Tang, Bing Yin, and Xianfeng Tang. 2023b. Amazon-m2: A multilingual multi-… find
  17. Lei Li, Yongfeng Zhang, and Li Chen. 2020. Generate neural template explanations for recommendation. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM ’20, page 755–764, New York, NY, USA. Association for Computing Machinery. find
  18. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023a. Visual instruction tuning. Preprint, arXiv:2304.08485.
  19. Xin Liu, Zheng Li, Yifan Gao, Jingfeng Yang, Tianyu Cao, Zhengyang Wang, Bing Yin, and Yangqiu Song. 2023b. Enhancing user intent capture in session-based recommendation with attribute patterns. Preprint, arXiv:2312.16199. — [arXiv:2312.16199](https://arxiv.org/abs/2312.16199) find
  20. OpenAI. 2024. Gpt-4o mini: advancing cost-efficient intelligence. OpenAI. find
  21. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Ja… — GPT-4 Technical Report
  22. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng… find
  23. Soyeon Shim, Mary Ann Eastlick, Sherry L Lotz, and Patricia Warrington. 2001. An online prepurchase intentions model: The role of intention to search. Journal of Retailing, 77(3):397–416. find
  24. Zhu Sun, Hongyang Liu, Xinghua Qu, Kaidong Feng, Yan Wang, and Yew Soon Ong. 2024. Large language models for intent-driven session recommendations. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 324–334, New York, N… find
  25. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, Johan Ferret, Peter Liu, Pouya Tafti, Abe Friesen, Michelle Casbon, Sabela Ramos, Ravin Kumar, Charline Le Lan, Sammy Jerome, Anton T… find
  26. Dongjing Wang, Haojiang Yao, Dongjin Yu, Shiyu Song, He Weng, Guandong Xu, and Shuiguang Deng. 2025a. Graph intention embedding neural network for tag-aware recommendation. Neural Networks, 184:107062. find
  27. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024a. Qwen2-vl: Enhancing vision-language model’s perception of the…
  28. Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, and Yangqiu Song. 2025b. Ecomscriptbench: A multi-task benchmark for e-commerce script planning via step-wise… find
  29. Weiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song, and Antoine Bosselut. 2023a. CAR: conceptualization-augmented reasoner for zero-shot commonsense question answering. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, p… find
  30. Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, and Yangqiu Song. 2024b. CANDLE: iterative conceptualization and instantiation distillation from large language models for commonsense reasoning. In Proceedi… find
  31. Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, and Yangqiu Song. 2025c. On the role of entity and event level conceptualization in generalizable reasoning: A survey of tasks, methods, applications, and future directions. In Find… find
  32. Weiqi Wang, Tianqing Fang, Baixuan Xu, Chun Yi Louis Bo, Yangqiu Song, and Lei Chen. 2023b. CAT: A contextualized conceptualization and instantiation framework for commonsense reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers… find
  33. Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao, Priyanka Nigam, Bing Yin, Lihong Li, and Yangqiu Song. 2026a. Heapa: Difficulty-aware heap sampling and on-policy query augmentation for LLM reinfo… — [arXiv:2601.22448](https://arxiv.org/abs/2601.22448) find
  34. Weiqi Wang, Jiefu Ou, Yangqiu Song, Benjamin Van Durme, and Daniel Khashabi. 2026b. arxiv2table: Toward realistic benchmarking and evaluation for llm-based literature-review table generation. Preprint, arXiv:2504.10284.
  35. Weiqi Wang and Yangqiu Song. 2025. MARS: benchmarking the metaphysical reasoning abilities of language models with a multi-task evaluation dataset. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27 -… find
  36. Yu Wang, Amin Javari, Janani Balaji, Walid Shalaby, Tyler Derr, and Xiquan Cui. 2024c. Knowledge graph-based session recommendation with session-adaptive propagation. In Companion Proceedings of the ACM Web Conference 2024, WWW ’24, page 264–273, New York, NY, USA. Association for Computing Machiner… find
  37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
  38. Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, and Yangqiu Song. 2024. MIND: Multimodal shopping intention distillation from large vision-language models for E-commerce purchase un… find
  39. Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, and Bing Yin. 2023. Folkscope: Intention knowledge graph construction for e-commerce commonsense discovery. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14… find
  40. Chenwei Zhang, Wei Fan, Nan Du, and Philip S. Yu. 2016. Mining user intentions from medical queries: A neural network based heterogeneous jointly modeling approach. In Proceedings of the 25th International Conference on World Wide Web, WWW ’16, page 1373–1384, Republic and Canton of Geneva, CHE. Int… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yang-2026-sessionintentbench-multi-task-inter-session/