Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PAP-REC: Personalized Automatic Prompt for Recommendation Language Model (2402.00284v1)

Published 1 Feb 2024 in cs.IR, cs.AI, and cs.LG

Abstract: Recently emerged prompt-based Recommendation LLMs (RLM) can solve multiple recommendation tasks uniformly. The RLMs make full use of the inherited knowledge learned from the abundant pre-training data to solve the downstream recommendation tasks by prompts, without introducing additional parameters or network training. However, handcrafted prompts require significant expertise and human effort since slightly rewriting prompts may cause massive performance changes. In this paper, we propose PAP-REC, a framework to generate the Personalized Automatic Prompt for RECommendation LLMs to mitigate the inefficiency and ineffectiveness problems derived from manually designed prompts. Specifically, personalized automatic prompts allow different users to have different prompt tokens for the same task, automatically generated using a gradient-based method. One challenge for personalized automatic prompt generation for recommendation LLMs is the extremely large search space, leading to a long convergence time. To effectively and efficiently address the problem, we develop surrogate metrics and leverage an alternative updating schedule for prompting recommendation LLMs. Experimental results show that our PAP-REC framework manages to generate personalized prompts, and the automatically generated prompts outperform manually constructed prompts and also outperform various baseline recommendation models. The source code of the work is available at https://github.com/rutgerswiselab/PAP-REC.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. Steffen Rendle. Factorization machines. In 2010 IEEE International conference on data mining, pages 995–1000. IEEE, 2010.
  2. Jerome H Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232, 2001.
  3. Practical lessons from predicting clicks on ads at facebook. In Proceedings of the eighth international workshop on data mining for online advertising, pages 1–9, 2014.
  4. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 2017.
  5. Deep learning. nature, 521(7553):436–444, 2015.
  6. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems, pages 7–10, 2016.
  7. Deep learning based recommender system: A survey and new perspectives. ACM computing surveys (CSUR), 52(1):1–38, 2019.
  8. Recommendation as language processing (rlp): A unified pretrain, personalized prompt & predict paradigm (p5). In Proceedings of the Sixteenth ACM Conference on Recommender Systems, 2022.
  9. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084, 2022.
  10. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586, 2021.
  11. Prompt programming for large language models: Beyond the few-shot paradigm. In Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pages 1–7, 2021.
  12. Differentiable prompt makes pre-trained language models better few-shot learners. arXiv preprint arXiv:2108.13161, 2021.
  13. Warp: Word-level adversarial reprogramming. arXiv preprint arXiv:2101.00121, 2021.
  14. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190, 2021.
  15. Gpt understands, too. arXiv preprint arXiv:2103.10385, 2021.
  16. Factual probing is [mask]: Learning vs. learning to recall. In North American Association for Computational Linguistics (NAACL), 2021.
  17. Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9):2337–2348, 2022.
  18. How can we know what language models know? Transactions of the Association for Computational Linguistics, 8:423–438, 2020.
  19. AutoPrompt: Eliciting knowledge from language models with automatically generated prompts. In Empirical Methods in Natural Language Processing (EMNLP), 2020.
  20. Bartscore: Evaluating generated text as text generation. Advances in Neural Information Processing Systems, 34:27263–27277, 2021.
  21. Making pre-trained language models better few-shot learners. In Association for Computational Linguistics (ACL), 2021.
  22. PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains. Transactions of the Association for Computational Linguistics, 10:414–433, 04 2022.
  23. Promptgen: Automatically generate prompts using generative models. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 30–37, 2022.
  24. Rlprompt: Optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:2205.12548, 2022.
  25. Pointclip v2: Adapting clip for powerful 3d open-world learning. arXiv preprint arXiv:2211.11682, 2022.
  26. Automatic chain of thought prompting in large language models. In The Eleventh International Conference on Learning Representations (ICLR 2023), 2023.
  27. Universal adversarial triggers for attacking and analyzing NLP. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2153–2162, Hong Kong, China, November 2019. Association for Computational Linguistics.
  28. Segment-based injection attacks against collaborative filtering recommender systems. In Fifth IEEE International Conference on Data Mining (ICDM’05), pages 4–pp. IEEE, 2005.
  29. Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446, 2002.
  30. Information retrieval: Implementing and evaluating search engines. Mit Press, 2016.
  31. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.
  32. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  33. OpenAI Josh et al. Gpt-4 technical report, 2023.
  34. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(140):1–67, 2020.
  35. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207, 2021.
  36. Scaling instruction-finetuned language models, 2022.
  37. Llama: Open and efficient foundation language models, 2023.
  38. Llama 2: Open foundation and fine-tuned chat models, 2023.
  39. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  40. A survey on evaluation of large language models. arXiv preprint arXiv:2307.03109, 2023.
  41. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  42. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046, 2023.
  43. How can recommender systems benefit from large language models: A survey. arXiv preprint arXiv:2306.05817, 2023.
  44. A survey on large language models for recommendation. arXiv preprint arXiv:2305.19860, 2023.
  45. Language models as recommender systems: Evaluations and limitations. In I (Still) Can’t Believe It’s Not Better! NeurIPS 2021 Workshop, 2021.
  46. Ctr-bert: Cost-effective knowledge distillation for billion-parameter teacher models. In NeurIPS Efficient Natural Language and Speech Processing Workshop, 2021.
  47. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
  48. Gpt4rec: A generative framework for personalized recommendation and user interests interpretation. arXiv preprint arXiv:2304.03879, 2023.
  49. Personalized prompt learning for explainable recommendation. arXiv preprint arXiv:2202.07371, 2022.
  50. Zero-shot recommendation as language modeling. In European Conference on Information Retrieval, pages 223–230. Springer, 2022.
  51. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447, 2023.
  52. Tabllm: Few-shot classification of tabular data with large language models. In International Conference on Artificial Intelligence and Statistics, pages 5549–5581. PMLR, 2023.
  53. Do llms understand user preferences? evaluating llms on user rating prediction. arXiv preprint arXiv:2305.06474, 2023.
  54. Commonsense knowledge mining from pretrained models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1173–1178, Hong Kong, China, November 2019. Association for Computational Linguistics.
  55. Bertese: Learning to speak to bert. arXiv preprint arXiv:2103.05327, 2021.
  56. Conditional prompt learning for vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16816–16825, 2022.
  57. Exploring the upper limits of text-based collaborative filtering using large language models: Discoveries and insights. arXiv preprint arXiv:2305.11700, 2023.
  58. Large language models for generative recommendation: A survey and visionary discussions. arXiv preprint arXiv:2309.01157, 2023.
  59. Generative sequential recommendation with gptrec. arXiv preprint arXiv:2306.11114, 2023.
  60. Learning vector-quantized item representation for transferable sequential recommenders. In Proceedings of the ACM Web Conference 2023, pages 1162–1171, 2023.
  61. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence, 33(1):117–128, 2010.
  62. How to index item ids for recommendation foundation models. arXiv preprint arXiv:2305.06569, 2023.
  63. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939, 2015.
  64. Yongfeng Zhang and Xu Chen. Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval, 14(1):1–101, 2020.
  65. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pages 452–461, 2009.
  66. Efficient neural architecture search via parameters sharing. In International Conference on Machine Learning, pages 4095–4104. PMLR, 2018.
  67. Autolossgen: Automatic loss function generation for recommender systems. SIGIR, 2022.
  68. S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 1893–1902, 2020.
  69. Generate neural template explanations for recommendation. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 755–764, 2020.
  70. Personalized transformer for explainable recommendation. arXiv preprint arXiv:2105.11601, 2021.
  71. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, pages 83–92, 2014.
  72. Do users rate or review? boost phrase-level sentiment labeling with review-level sentiment classification. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, pages 1027–1030, 2014.
  73. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318, 2002.
  74. Chin-Yew Lin. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81, 2004.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Zelong Li (24 papers)
  2. Jianchao Ji (14 papers)
  3. Yingqiang Ge (36 papers)
  4. Wenyue Hua (51 papers)
  5. Yongfeng Zhang (163 papers)
Citations (4)
View on Semantic Scholar
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - rutgerswiselab/PAP-REC (10 stars)