How to Index Item IDs for Recommendation Foundation Models
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Recommendation foundation model utilizes large language models (LLM) for recommendation by converting recommendation tasks into natural language tasks. It enables generative recommendation which directly generates the item(s) to recommend rather than calculating a ranking score for each and every candidate item as in traditional recommendation models, simplifying the recommendation pipeline from multi-stage filtering to single-stage filtering. To avoid generating excessively long text and hallucinated recommendations when deciding which item(s) to recommend, creating LLM-compatible item IDs to uniquely identify each item is essential for recommendation foundation models. In this study, we systematically examine the item ID creation and indexing problem for recommendation foundation models, using P5 as an example of the backbone LLM. To emphasize the importance of item indexing, we first discuss the issues of several trivial item indexing methods, such as random indexing, title indexing, and independent indexing. We then propose four simple yet effective solutions, including sequential indexing, collaborative indexing, semantic (content-based) indexing, and hybrid indexing. Our study highlights the significant influence of item indexing methods on the performance of LLM-based recommendation, and our results on real-world datasets validate the effectiveness of our proposed solutions. The research also demonstrates how recent advances on language modeling and traditional IR principles such as indexing can help each other for better learning and inference. Source code and data are available at https://github.com/Wenyueh/LLM-RecSys-ID.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The MovieLens Datasets: History and Context
Harper, F. M., & Konstan, J. A. (2016) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/2827872 · Cited by 6,627
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Deep Neural Networks for YouTube Recommendations
Covington, P., Adams, J., & Sargin, E. (2016) · Proceedings of the 10th ACM Conference on Recommender Systems · doi:10.1145/2959100.2959190 · Cited by 3,539
Deep Learning Based Recommender System: A Survey and New Perspectives
Zhang, S., Yao, L., Sun, A., & Tay, Y. (2020) · ACM Computing Surveys · doi:10.1145/3285029 · Cited by 3,485
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
Sun, F., Liu, J., Wu, J., Pei, C., Lin, X., Ou, W., & Jiang, P. (2019) · Proceedings of the 28th ACM International Conference on Information and Knowledge Management · doi:10.1145/3357384.3357895 · Cited by 2,558 · cited 2×
“Sequential-based matching methods usually encode a user’s interaction history into a vector using a sequential model first and then make recommendations by matching the vector with the vector embeddings of candidate items [3, 11, 13, 15, 25, 29].”
MethodScaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · cited 1×
“FoundationModels such as Large LanguageModels (LLMs) [5, 6, 30] have significantly impacted research areas such as natural language processing (NLP) and computer vision (CV) [21], and have been applied to various recommender system (RS) tasks.”
BackgroundNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2021) · arXiv · doi:10.48550/arxiv.2109.07958 · Cited by 899 · cited 1×
“, a product title/description could include tens/hundreds of words and a news article could include thousands of words), we can hardly expect an LLM to generate the complete and exact item description when deciding which item(s) to recommend, because the generated text may not even correspond to a real existing item i…”
BackgroundRecommender Systems: An Introduction
Jannach, D., Zanker, M., Felfernig, A., & Friedrich, G. (2010) · doi:10.1017/cbo9780511763113 · Cited by 886
Geng, S., Liu, S., Fu, Z., Ge, Y., & Zhang, Y. (2022) · Proceedings of the 16th ACM Conference on Recommender Systems · doi:10.1145/3523227.3546767 · Cited by 556
Self-citation
Cited by
Recommender Systems in the Era of Large Language Models (LLMs)
Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao, X., Tang, J., et al. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3392335 · Cited by 481
“Based on P5, Hua et al. put forward four straightforward but effective indexing solutions [63]: sequential indexing, collaborative indexing, semantic (content-based) indexing, and hybrid indexing, underscoring the significance of indexing methods.”
Large Language Models are Zero-Shot Rankers for Recommender Systems
Hou, Y., Zhang, J., Lin, Z., Lu, H., Xie, R., McAuley, J., & Zhao, W. X. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-56060-6_24 · Cited by 327
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
Zheng, B., Hou, Y., Lu, H., Chen, Y., Zhao, W. X., Chen, M., & Wen, J.-R. (2024) · 2024 IEEE 40th International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00118 · Cited by 143
“To address this issue, we borrow the idea of existing studies [15], [23], [37] to learn indices associated with latent semantics for items.”
BackgroundMethodInfluentialDecoding in Latent Spaces for Efficient Inference in LLM-based Recommendation
Wang, C., Zhang, Y., Wang, Z., Shi, T., Bao, K., Feng, F., & Chua, T.-S. (2025) · arXiv · doi:10.48550/arxiv.2509.11524 · Cited by 2
“(3) LLM-Based Generative Recommenders generate natural language recommendations without predefined items, offering innovative potential (Bao et al., 2023a, 2024; Zheng et al., 2024; Hua et al., 2023; Zhu et al., 2024; Zhang et al., 2025b).”
Self-citation
Metadata
- Authors
- Hua, W., Xu, S., Ge, Y., & Zhang, Y.
- Venue
- Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region
- Publisher
- ACM
- Published
- 2023-11-26
- Pages
- 195-204
- OpenAlex
- W4376312036
- Cited by
- 61
- References
- 12
- FWCI
- 16.26
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: How to Index Item IDs for Recommendation Foundation Models. https://app.cochat.ai/papers/10.1145/3624918.3625339
- The paper
- Hua, W., Xu, S., Ge, Y., & Zhang, Y. (2023). How to Index Item IDs for Recommendation Foundation Models. Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region. https://doi.org/10.1145/3624918.3625339
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.