Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Recommender system plays a vital role in various online services. However, its insulated nature of training and deploying separately within a specific closed domain limits its access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating reasoning capabilities. Nevertheless, previous attempts to directly use LLMs as recommenders cannot meet the inference latency demand of industrial recommender systems. In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs — the reasoning knowledge on user preferences and the factual knowledge on items. We introduce factorization prompting to elicit accurate reasoning on user preferences. The generated reasoning and factual knowledge are effectively transformed and condensed into augmented vectors by a hybrid-expert adaptor in order to be compatible with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments show that KAR significantly outperforms the state-of-the-art baselines and is compatible with a wide range of recommendation algorithms. We deploy KAR to Huawei’s news and music recommendation platforms and gain a 7% and 1.7% improvement in the online A/B test, respectively.
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
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453 · cited 1×
“This section reviews studies on recent advances in recommendation with pretrained language models (PLMs).”
Adaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 2×
“Moreover, the knowledge generated by LLMs can sometimes be unreliable or misleading due to the hallucination problem [21].”
BackgroundSurvey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y., Chen, D., Dai, W., et al. (2022) · arXiv · doi:10.48550/arxiv.2202.03629 · Cited by 4,981
Cumulated gain-based evaluation of IR techniques
Järvelin, K., & Kekäläinen, J. (2002) · ACM Transactions on Information Systems · doi:10.1145/582415.582418 · Cited by 4,841 · cited 1×
“As for reranking task, several widely used metrics, NDCG@K [28] and MAP@K [72], are adopted, following previous work [1, 51, 70].”
MethodLLaMA: 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
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
Rendle, S. (2010) · 2010 IEEE International Conference on Data Mining · doi:10.1109/icdm.2010.127 · Cited by 3,189
Deep Interest Network for Click-Through Rate Prediction
Zhou, G., Zhu, X., Song, C., Fan, Y., Zhu, H., Ma, X., Yan, Y., Jin, J., Li, H., & Gai, K. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219823 · Cited by 2,128
Self-citationA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093 · cited 1×
“Recent rapid developments in large languagemodels (LLMs) have revolutionized the learning paradigm of various research fields and show great potential in bridging the gap between classical recommenders and open-world knowledge [51].”
BackgroundSparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Knowledge Graph Convolutional Networks for Recommender Systems
Wang, H., Zhao, M., Xie, X., Li, W., & Guo, M. (2019) · The World Wide Web Conference · doi:10.1145/3308558.3313417 · Cited by 1,424
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
A Survey on Large Language Models for Recommendation
Wu, L., Zheng, Z., Qiu, Z., Wang, H., Gu, H., Shen, T., Qin, C., Zhu, C., Zhu, H., Liu, Q., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.19860 · Cited by 515
Self-citationA survey on large language models for recommendation
Wu, L., Zheng, Z., Qiu, Z., Wang, H., Gu, H., Shen, T., Qin, C., Zhu, C., Zhu, H., Liu, Q., et al. (2024) · World Wide Web · doi:10.1007/s11280-024-01291-2 · Cited by 515
Self-citationRecommender 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 · cited 1×
“This section reviews studies on recent advances in recommendation with pretrained language models (PLMs).”
Towards Reasoning in Large Language Models: A Survey
Huang, J., & Chang, K. C.-C. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.67 · Cited by 428
Towards Reasoning in Large Language Models: A Survey
Huang, J., & Chang, K. C.-C. (2022) · arXiv · doi:10.48550/arxiv.2212.10403 · Cited by 428
Self-supervised learning for recommender systems: A survey
Yu, J., Yin, H., Xia, X., Chen, T., Li, J., & Huang, Z. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3282907 · Cited by 413 · cited 1×
“This section reviews studies on recent advances in recommendation with pretrained language models (PLMs).”
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
Towards Universal Sequence Representation Learning for Recommender Systems
Hou, Y., Mu, S., Zhao, W. X., Li, Y., Ding, B., & Wen, J.-R. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539381 · Cited by 313 · cited 8×
“We compare KAR with some baselines that leverage pretraining techniques with text or behavioral data to enhance the recommendation models, such as P5 [9], UniSRec [16], VQRec [15].”
BackgroundMethodInfluentialMeasuring and Narrowing the Compositionality Gap in Language Models
Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N., & Lewis, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.378 · Cited by 303
Measuring and Narrowing the Compositionality Gap in Language Models
Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N. A., & Lewis, M. (2022) · arXiv · doi:10.48550/arxiv.2210.03350 · Cited by 294 · cited 3×
“Considering the reasoning knowledge, according to [32], LLMs often suffer from the compositional gap where the model fails at generating the correct answer to the compositional question but”
BackgroundMethodLearning Vector-Quantized Item Representation for Transferable Sequential Recommenders
Hou, Y., He, Z., McAuley, J., & Zhao, W. X. (2023) · Proceedings of the ACM Web Conference 2023 · doi:10.1145/3543507.3583434 · Cited by 172 · cited 5×
“We compare KAR with some baselines that leverage pretraining techniques with text or behavioral data to enhance the recommendation models, such as P5 [9], UniSRec [16], VQRec [15].”
BackgroundMethodInfluentialZeng, W., Ren, X., Su, T., Wang, H., Liao, Y., Wang, Z., Jiang, X., Yang, Z., Wang, K., Zhang, X., et al. (2021) · arXiv · doi:10.48550/arxiv.2104.12369 · Cited by 172 · cited 3×
“Besides, while experiments may involve the use of external APIs on public datasets, real-world implementations usually rely on in-house models, e.g. , we utilize Huawei’s own LLM PanGu[73] for online A/B test as described in section 5.3, preventing the leakage of user privacy information through external APIs.”
MethodInfluentialSelf-citationWhat Does it Mean for a Language Model to Preserve Privacy?
Brown, H., Lee, K., Mireshghallah, F., Shokri, R., & Tramèr, F. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3534642 · Cited by 165
U-BERT: Pre-training User Representations for Improved Recommendation
Qiu, Z., Wu, X., Gao, J., & Fan, W. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i5.16557 · Cited by 112
AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems
Zhang, J., Hou, Y., Xie, R., Sun, W., McAuley, J., Zhao, W. X., Lin, L., & Wen, J.-R. (2024) · Proceedings of the ACM Web Conference 2024 · doi:10.1145/3589334.3645537 · Cited by 94
Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
Gao, Y., Sheng, T., Xiang, Y., Xiong, Y., Wang, H., & Zhang, J. (2023) · arXiv · doi:10.48550/arxiv.2303.14524 · Cited by 79
Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
Wang, L., & Lim, E.-P. (2023) · arXiv · doi:10.48550/arxiv.2304.03153 · Cited by 27
Ding, H., Ma, Y., Deoras, A., Wang, Y., & Wang, H. (2021) · arXiv · doi:10.48550/arxiv.2105.08318 · Cited by 19
Cited by
A survey on large language models for recommendation
Wu, L., Zheng, Z., Qiu, Z., Wang, H., Gu, H., Shen, T., Qin, C., Zhu, C., Zhu, H., Liu, Q., et al. (2024) · World Wide Web · doi:10.1007/s11280-024-01291-2 · Cited by 515
Self-citationA Survey on Large Language Models for Recommendation
Wu, L., Zheng, Z., Qiu, Z., Wang, H., Gu, H., Shen, T., Qin, C., Zhu, C., Zhu, H., Liu, Q., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.19860 · Cited by 515
Self-citationRecommender 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
When large language models meet personalization: perspectives of challenges and opportunities
Chen, J., Liu, Z., Huang, X., Wu, C., Liu, Q., Jiang, G., Pu, Y., Lei, Y., Chen, X., Wang, X., et al. (2024) · World Wide Web · doi:10.1007/s11280-024-01276-1 · Cited by 367
“Existingwork[80]prompts largelanguagemodelstogeneratefactualknowledgeaboutmoviestoenhancetheperfor-manceofCTRpredictionmodels.”
A Survey of Personalization: From RAG to Agent
Li, X., Jia, P., Xu, D., Wen, Y., Zhang, Y., Zhang, W., Wang, W., Wang, Y., Du, Z., Li, X., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.10147 · Cited by 52
Self-citation
Metadata
- Authors
- Xi, Y., Liu, W., Lin, J., Cai, X., Zhu, H., Zhu, J., Chen, B., Tang, R., Zhang, W., & Yu, Y.
- Venue
- 18th ACM Conference on Recommender Systems
- Publisher
- ACM
- Published
- 2024-10-08
- Pages
- 12-22
- OpenAlex
- W4403220611
- Cited by
- 151
- References
- 32
- FWCI
- 59.35
- 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
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.