Elamur Research⌕
☰
home / papers / 2026 / GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models

GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models

Paper · 2026 · Yuan Zhong, Chuanwei Ruan, Moein Hasani et al.

Summary

Online grocery shopping is highly repetitive: customers regularly restock staples and fill baskets across complementary categories. Item-level recommenders struggle with this pattern at scale, so the authors (Penn State, Instacart, Evenup) target category-level recommendation. In this setting, a model predicts which categories a user will buy in the next session, and items are then placed into those categories. GrocLM is built on a LLaMA 3 backbone and fine-tuned with LoRA in two stages. The first stage teaches the model per-category repurchase cycles, expressed as the mean and standard deviation of days between purchases, averaged over users. The second stage trains it on sequential purchase histories paired with the user's current search queries. A trie-based mask combined with beam search restricts generation to valid category labels, so outputs never need fuzzy matching afterward. Evaluations on proprietary production data and a public benchmark show consistent gains over strong baselines, and a live deployment confirmed the benefit. The work shows that LLMs can operate within a structured, constrained recommendation pipeline in production.

Key points

  • In a live restocking task, GrocLM raised cart-adds per impression by 7.5% relative to the production model. It stays efficient because it generates all categories in a single joint pass.
  • Storing repurchase-cycle statistics in the weights works far better than placing them in the prompt. On F1@10, the LoRA version scores 0.111 while the in-context-learning variant scores 0.007; on R@10 the figures are 0.231 versus 0.012.
  • The trie-constrained decoder prevents near-miss outputs such as "snack" versus "snacks." Without it, such slips would count as false negatives.
  • The authors varied training data from 500 to 8,000 users:
    • Two Tower is slightly ahead with very few users (500–1,000).
    • GrocLM leads once there are more than about 3,000 users.
    • Two Tower and SASRec level off around 5,000 users, while GrocLM keeps improving.
  • The paper appears in the ACL 2026 Industry Track (pages 371–385). Listed future work covers personalization in low-resource settings and finer control over categories.

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

🎓Pennsylvania State UniversityState College · United States67 works · 5,865 citations

Also on the byline: Instacart.

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksInformation Systems · 1,730 works

Cite

Cite as Yuan Zhong, Chuanwei Ruan, Moein Hasani, Tejaswi Tenneti, Haixun Wang and Fenglong Ma. 2026. GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-industry.25

@inproceedings{zhong2026groclm,
  title = {{GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models}},
  author = {Yuan Zhong, Chuanwei Ruan, Moein Hasani, Tejaswi Tenneti, Haixun Wang and Fenglong Ma},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-industry.25},
  url = {https://doi.org/10.18653/v1/2026.acl-industry.25}
}

References

66 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. 2021. Instacart online grocery basket analysis dataset. find
  2. Akiko Aizawa. 2003. An information-theoretic perspective of tf–idf measures. Information Processing & Management, 39(1):45–65. find
  3. Keqin Bao, Ming Yan, Yang Zhang, Jizhi Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2024. Real-time personalization for llm-based recommendation with customized in-context learning. arXiv preprint arXiv:2410.23136. — [arXiv:2410.23136](https://arxiv.org/abs/2410.23136) find
  4. Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1007–1014.
  5. Jin Chen, Zheng Liu, Xu Huang, Chenwang Wu, Qi Liu, Gangwei Jiang, Yuanhao Pu, Yuxuan Lei, Xiaolong Chen, Xingmei Wang, and 1 others. 2024. When large language models meet personalization: Perspectives of challenges and opportunities. World Wide Web, 27(4):42. find
  6. Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084. — [arXiv:2205.08084](https://arxiv.org/abs/2205.08084) find
  7. Sunhao Dai, Ninglu Shao, Haiyuan Zhao, Weijie Yu, Zihua Si, Chen Xu, Zhongxiang Sun, Xiao Zhang, and Jun Xu. 2023. Uncovering chatgpt’s capabilities in recommender systems. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1126–1132. find
  8. Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2020. Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904. find
  9. Yashar Deldjoo, Zhankui He, Julian McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, René Vidal, Maheswaran Sathiamoorthy, Atoosa Kasirzadeh, and Silvia Milano. 2024. A review of modern recommender systems using generative models (gen-recsys). In Proceedings of the 30th ACM SIGKDD Conference on Kn… find
  10. Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  11. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  12. Yixing Fan, Xiaohui Xie, Yinqiong Cai, Jia Chen, Xinyu Ma, Xiangsheng Li, Ruqing Zhang, Jiafeng Guo, and 1 others. 2022. Pre-training methods in information retrieval. Foundations and Trends® in Information Retrieval, 16(3):178–317. find
  13. Shijie Geng, Shuchang Liu, Zuohui Fu, Yingqiang Ge, and Yongfeng Zhang. 2022. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5). In Proceedings of the 16th ACM Conference on Recommender Systems, pages 299–315. find
  14. Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In Proceedings of the 22nd ACM international conference on Information & Knowledge Management, pages 2333–2338. find
  15. Jiafeng Guo, Yinqiong Cai, Yixing Fan, Fei Sun, Ruqing Zhang, and Xueqi Cheng. 2022. Semantic models for the first-stage retrieval: A comprehensive review. ACM Transactions on Information Systems (TOIS), 40(4):1–42. find
  16. Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2019. Poly-encoders: Transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring. arXiv preprint arXiv:1905.01969. find
  17. Jiafeng Guo, Yixing Fan, Qingyao Ai, and W Bruce Croft. 2016. A deep relevance matching model for ad-hoc retrieval. In Proceedings of the 25th ACM international on conference on information and knowledge management, pages 55–64. find
  18. Wang-Cheng Kang and Julian McAuley. 2018. Self-attentive sequential recommendation. In 2018 IEEE international conference on data mining (ICDM), pages 197–206. IEEE. find
  19. Jiafeng Guo, Yixing Fan, Xiang Ji, and Xueqi Cheng. 2019. Matchzoo: A learning, practicing, and developing system for neural text matching. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1297–1300. find
  20. Deepesh V Hada and Shirish K Shevade. 2021. Rexplug: Explainable recommendation using plug-and-play language model. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 81–91. find
  21. Jesse Harte, Wouter Zorgdrager, Panos Louridas, Asterios Katsifodimos, Dietmar Jannach, and Marios Fragkoulis. 2023. Leveraging large language models for sequential recommendation. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 1096–1102. find
  22. Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 639–648. find
  23. Sebastian Hofstätter, Omar Khattab, Sophia Althammer, Mete Sertkan, and Allan Hanbury. 2022. Introducing neural bag of whole-words with colberter: Contextualized late interactions using enhanced reduction. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management,… find
  24. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
  25. Wenyue Hua, Shuyuan Xu, Yingqiang Ge, and Yongfeng Zhang. 2023. How to index item ids for recommendation foundation models. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pages 195–204. find
  26. Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, and Derek Zhiyuan Cheng. 2023. Do llms understand user preferences? evaluating llms on user rating prediction. arXiv preprint arXiv:2305.06474. — [arXiv:2305.06474](https://arxiv.org/abs/2305.06474) find
  27. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906.
  28. Omar Khattab and Matei Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 39– 48.
  29. Sein Kim, Hongseok Kang, Seungyoon Choi, Donghyun Kim, Minchul Yang, and Chanyoung Park. 2024. Large language models meet collaborative filtering: An efficient all-round llm-based recommender system. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 1395–… find
  30. Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, and Wook-Shin Han. 2022. Autoregressive image generation using residual quantization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11523–11532. find
  31. 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, pages 755–764. find
  32. Lei Li, Yongfeng Zhang, and Li Chen. 2023. Personalized prompt learning for explainable recommendation. ACM Transactions on Information Systems, 41(4):1–26. find
  33. Zhongyang Li, Xiao Ding, Kuo Liao, Bing Qin, and Ting Liu. 2021. Causalbert: Injecting causal knowledge into pre-trained models with minimal supervision. arXiv preprint arXiv:2107.09852. — [arXiv:2107.09852](https://arxiv.org/abs/2107.09852) find
  34. Junling Liu, Chao Liu, Peilin Zhou, Renjie Lv, Kang Zhou, and Yan Zhang. 2023. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149. — [arXiv:2304.10149](https://arxiv.org/abs/2304.10149) find
  35. Tie-Yan Liu and 1 others. 2009. Learning to rank for information retrieval. Foundations and Trends® in Information Retrieval, 3(3):225–331. find
  36. Man Luo, Arindam Mitra, Tejas Gokhale, and Chitta Baral. 2022. Improving biomedical information retrieval with neural retrievers. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11038–11046. find
  37. Zhiming Mao, Huimin Wang, Yiming Du, and Kam-Fai Wong. 2023. Unitrec: A unified text-to-text transformer and joint contrastive learning framework for text-based recommendation. arXiv preprint arXiv:2305.15756. find
  38. Bhaskar Mitra and Nick Craswell. 2017. Neural models for information retrieval. arXiv preprint arXiv:1705.01509. — [arXiv:1705.01509](https://arxiv.org/abs/1705.01509) find
  39. Jianmo Ni, Gustavo Hernandez Abrego, Noah Constant, Ji Ma, Keith B Hall, Daniel Cer, and Yinfei Yang. 2021a. Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877.
  40. Jianmo Ni, Jiacheng Li, and Julian McAuley. 2019. Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (…
  41. Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernández Ábrego, Ji Ma, Vincent Y Zhao, Yi Luan, Keith B Hall, Ming-Wei Chang, and 1 others. 2021b. Large dual encoders are generalizable retrievers. arXiv preprint arXiv:2112.07899.
  42. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543.
  43. Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191.
  44. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67.
  45. Shashank Rajput, Nikhil Mehta, Anima Singh, Raghu-nandan Hulikal Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, and 1 others. 2024. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, 36. find
  46. Juan Ramos and 1 others. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, volume 242, pages 29–48. Citeseer. find
  47. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  48. Stephen Robertson. 2004. Understanding inverse document frequency: on theoretical arguments for idf. Journal of documentation, 60(5):503–520. find
  49. Gerard Salton. 1962. Some experiments in the generation of word and document associations. In Proceedings of the December 4-6, 1962, fall joint computer conference, pages 234–250. find
  50. Gerard Salton, Anita Wong, and Chung-Shu Yang. 1975. A vector space model for automatic indexing. Communications of the ACM, 18(11):613–620. find
  51. Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, and Lucas Dixon. 2023. Large language models are competitive near cold-start recommenders for language-and item-based preferences. In Proceedings of the 17th ACM conference on recommender systems, pages 890–896. find
  52. Zihua Si, Zhongxiang Sun, Jiale Chen, Guozhang Chen, Xiaoxue Zang, Kai Zheng, Yang Song, Xiao Zhang, and Jun Xu. 2023. Generative retrieval with semantic tree-structured item identifiers via contrastive learning. arXiv preprint arXiv:2309.13375. — [arXiv:2309.13375](https://arxiv.org/abs/2309.13375) find
  53. Damien Sileo, Wout Vossen, and Robbe Raymaekers. 2022. Zero-shot recommendation as language modeling. In European Conference on Information Retrieval, pages 223–230. Springer. find
  54. Juntao Tan, Shuyuan Xu, Wenyue Hua, Yingqiang Ge, Zelong Li, and Yongfeng Zhang. 2024. Towards llm-recsys alignment with textual id learning. arXiv preprint arXiv:2403.19021. — [arXiv:2403.19021](https://arxiv.org/abs/2403.19021) find
  55. A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems.
  56. Yidan Wang, Zhaochun Ren, Weiwei Sun, Jiyuan Yang, Zhixiang Liang, Xin Chen, Ruobing Xie, Su Yan, Xu Zhang, Pengjie Ren, and 1 others. 2024. Enhanced generative recommendation via content and collaboration integration. arXiv preprint arXiv:2403.18480. — [arXiv:2403.18480](https://arxiv.org/abs/2403.18480) find
  57. Chuhan Wu, Fangzhao Wu, Tao Qi, and Yongfeng Huang. 2021. Empowering news recommendation with pre-trained language models. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 1652–1656. find
  58. Likang Wu, Zhi Zheng, Zhaopeng Qiu, Hao Wang, Hongchao Gu, Tingjia Shen, Chuan Qin, Chen Zhu, Hengshu Zhu, Qi Liu, and 1 others. 2024. A survey on large language models for recommendation. World Wide Web, 27(5):60. find
  59. Shitao Xiao, Zheng Liu, Yingxia Shao, Tao Di, Bhuvan Middha, Fangzhao Wu, and Xing Xie. 2022. Training large-scale news recommenders with pretrained language models in the loop. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 4215–4225. find
  60. Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808.
  61. Andrew Yates, Rodrigo Nogueira, and Jimmy Lin. 2021. Pretrained transformers for text ranking: Bert and beyond. In Proceedings of the 14th ACM International Conference on web search and data mining, pages 1154–1156. find
  62. Jizhi Zhang, Keqin Bao, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 993–999. find
  63. Zihuai Zhao, Wenqi Fan, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Zhen Wen, Fei Wang, Xiangyu Zhao, Jiliang Tang, and 1 others. 2024. Recommender systems in the era of large language models (llms). IEEE Transactions on Knowledge and Data Engineering. find
  64. Bowen Zheng, Yupeng Hou, Hongyu Lu, Yu Chen, Wayne Xin Zhao, Ming Chen, and Ji-Rong Wen. 2024. Adapting large language models by integrating collaborative semantics for recommendation. In 2024 IEEE 40th International Conference on Data Engineering (ICDE), pages 1435–1448. IEEE. find
  65. Justin Zobel and Alistair Moffat. 2006. Inverted files for text search engines. ACM computing surveys (CSUR), 38(2):6–es. find
  66. Justin Zobel, Alistair Moffat, and Kotagiri Ramamohanarao. 1998. Inverted files versus signature files for text indexing. ACM Transactions on Database Systems (TODS), 23(4):453–490. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhong-2026-groclm-grocery-category-recommendation-e/