Large Language Models as Zero-Shot Conversational Recommenders
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
In this paper, we present empirical studies on conversational recommendation tasks using representative large language models in a zero-shot setting with three primary contributions. (1) Data: To gain insights into model behavior in "in-the-wild" conversational recommendation scenarios, we construct a new dataset of recommendation-related conversations by scraping a popular discussion website. This is the largest public real-world conversational recommendation dataset to date. (2) Evaluation: On the new dataset and two existing conversational recommendation datasets, we observe that even without fine-tuning, large language models can outperform existing fine-tuned conversational recommendation models. (3) Analysis: We propose various probing tasks to investigate the mechanisms behind the remarkable performance of large language models in conversational recommendation. We analyze both the large language models' behaviors and the characteristics of the datasets, providing a holistic understanding of the models' effectiveness, limitations and suggesting directions for the design of future conversational recommenders.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
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×
“The encouraging performance from the open-sourced LLMs [11, 68] also opens up the opportunities to further improve CRS performance via efficient tuning [3, 28] and collaborative filtering [36] ensembling.”
BackgroundScaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 2×
“In particular, existing work reveals language models’ performance and sample efficiency on downstream tasks can be improved simply through scaling up their parameter sizes [35].”
BackgroundThe 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
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
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
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
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Bajaj, P., Campos, D., Craswell, N., Deng, L., Gao, J., Liu, X., Majumder, R., McNamara, A., Mitra, B., Nguyen, T., et al. (2016) · arXiv · doi:10.48550/arxiv.1611.09268 · Cited by 2,473
Shortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
A 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
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Sparks 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
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., Gao, J., Liu, J., & Dolan, B. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2020.acl-demos.30 · Cited by 1,076
Competition-level code generation with AlphaCode
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Dal Lago, A., et al. (2022) · Science · doi:10.1126/science.abq1158 · Cited by 1,043
Competition-Level Code Generation with AlphaCode
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Lago, A. D., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.07814 · Cited by 1,043
Bias and Debias in Recommender System: A Survey and Future Directions
Chen, J., Dong, H., Wang, X., Feng, F., Wang, M., & He, X. (2023) · ACM Transactions on Information Systems · doi:10.1145/3564284 · Cited by 741 · cited 3×
“Compared to the target datasets, LLMs recommendations are more concentrated on popular items, which may cause further issues like the bias amplification loop [8].”
BackgroundMultitask Prompted Training Enables Zero-Shot Task Generalization
Sanh, V., Webson, A., Raffel, C., Bach, S. H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Scao, T. L., Raja, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.08207 · Cited by 612 · cited 1×
“Meanwhile, language models could further generalize to a wide range of unseen tasks by instruction tuning, learning to follow task instructions in natural language [52, 57].”
BackgroundCodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X
Zheng, Q., Xia, X., Zou, X., Dong, Y., Wang, S., Xue, Y., Shen, L., Wang, Z., Wang, A., Li, Y., et al. (2023) · Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3580305.3599790 · Cited by 563
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
Bao, K., Zhang, J., Zhang, Y., Wang, W., Feng, F., & He, X. (2023) · Proceedings of the 17th ACM Conference on Recommender Systems · doi:10.1145/3604915.3608857 · Cited by 469 · cited 4×
“Additionally, another study [3] on traditional recommendation systems suggests that LLMs are beneficial in a setting with many cold-start items.”
BackgroundInfluentialThe False Promise of Imitating Proprietary LLMs
Gudibande, A., Wallace, E., Snell, C., Geng, X., Liu, H., Abbeel, P., Levine, S., & Song, D. (2023) · arXiv · doi:10.48550/arxiv.2305.15717 · Cited by 377 · cited 1×
“finding that smaller distilled models via imitation learning cannot fully inherit larger models ability on downstream tasks [20].”
BackgroundCritiquing-based recommenders: survey and emerging trends
Chen, L., & Pu, P. (2012) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-011-9108-6 · Cited by 281 · cited 1×
“Typical traditional CRS setups include template-based CRS [13, 26, 37, 38, 70] and critiquing-based CRS [9, 42, 67].”
MethodLei, W., He, X., Miao, Y., Wu, Q., Hong, R., Kan, M.-Y., & Chua, T.-S. (2020) · Proceedings of the 13th International Conference on Web Search and Data Mining · doi:10.1145/3336191.3371769 · Cited by 253 · cited 1×
“Typical traditional CRS setups include template-based CRS [13, 26, 37, 38, 70] and critiquing-based CRS [9, 42, 67].”
MethodTowards Deep Conversational Recommendations
Li, R., Kahou, S., Schulz, H., Michalski, V., Charlin, L., & Pal, C. (2018) · arXiv · doi:10.48550/arxiv.1812.07617 · Cited by 242 · cited 23×
“• ReDIAL [41]: This model is released along with the ReDIAL dataset with an auto-encoder [58]-based recommender.”
BackgroundMethodResultInfluentialInteractive Path Reasoning on Graph for Conversational Recommendation
Lei, W., Zhang, G., He, X., Miao, Y., Wang, X., Chen, L., & Chua, T.-S. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403258 · Cited by 228 · cited 1×
“Typical traditional CRS setups include template-based CRS [13, 26, 37, 38, 70] and critiquing-based CRS [9, 42, 67].”
MethodTowards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
Wang, X., Zhou, K., Wen, J.-R., & Zhao, W. X. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539382 · Cited by 164 · cited 9×
“Note that we do not include more works [43, 50, 54] because UniCRS [64] is representative with similar results.”
BackgroundMethodResultInfluentialTransformer Memory as a Differentiable Search Index
Tay, Y., Tran, V., Dehghani, M., Ni, J., Bahri, D., Mehta, H., Qin, Z., Hui, K., Zhao, Z., Gupta, J., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1587 · Cited by 128
LaMP: When Large Language Models Meet Personalization
Salemi, A., Mysore, S., Bendersky, M., & Zamani, H. (2023) · arXiv · doi:10.48550/arxiv.2304.11406 · Cited by 109 · cited 1×
“This has captured the attention of the recommender systems community to explore the possibility of leveraging LLMs in recommendation or more general personalization tasks [3, 27, 34, 48, 56].”
BackgroundLaMP: When Large Language Models Meet Personalization
Salemi, A., Mysore, S., Bendersky, M., & Zamani, H. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.399 · Cited by 109
Is ChatGPT a Good Recommender? A Preliminary Study
Liu, J., Liu, C., Zhou, P., Lv, R., Zhou, K., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2304.10149 · Cited by 60
Generative Recommendation: Towards Next-generation Recommender Paradigm
Wang, W., Lin, X., Feng, F., He, X., & Chua, T.-S. (2023) · arXiv · doi:10.48550/arxiv.2304.03516 · Cited by 34
Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
Kang, W.-C., Ni, J., Mehta, N., Sathiamoorthy, M., Hong, L., Chi, E., & Cheng, D. Z. (2023) · arXiv · doi:10.48550/arxiv.2305.06474 · Cited by 28
M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
Cui, Z., Ma, J., Zhou, C., Zhou, J., & Yang, H. (2022) · arXiv · doi:10.48550/arxiv.2205.08084 · Cited by 27 · cited 1×
“Recently, there have been various attempts by the recommendation community to leverage large language models for recommendation, this includes both adapting architectures used by large language models [14, 19] and repurposing existing LLMs for recommendation [39, 48, 62].”
BackgroundLeveraging Large Language Models in Conversational Recommender Systems
Friedman, L., Ahuja, S., Allen, D., Tan, Z., Sidahmed, H., Long, C., Xie, J., Schubiner, G., Patel, A., Lara, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.07961 · Cited by 25
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
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
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
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
Self-citationHow Can Recommender Systems Benefit from Large Language Models: A Survey
Lin, J., Dai, X., Xi, Y., Liu, W., Chen, B., Zhang, H., Liu, Y., Wu, C., Li, X., Zhu, C., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3678004 · Cited by 242
Metadata
- Authors
- He, Z., Xie, Z., Jha, R., Steck, H., Liang, D., Feng, Y., Majumder, B. P., Kallus, N., & Mcauley, J.
- Venue
- Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
- Publisher
- ACM
- Published
- 2023-10-21
- Pages
- 720-730
- OpenAlex
- W4386081001
- Cited by
- 140
- References
- 37
- FWCI
- 37.31
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.