Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanism (2402.10548v1)

Published 16 Feb 2024 in cs.IR

Abstract: Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs. Deep learning-based personalized search methods have shown promise, but they rely heavily on abundant training data, making them susceptible to data sparsity challenges. This paper proposes a Cognitive Personalized Search (CoPS) model, which integrates LLMs with a cognitive memory mechanism inspired by human cognition. CoPS employs LLMs to enhance user modeling and user search experience. The cognitive memory mechanism comprises sensory memory for quick sensory responses, working memory for sophisticated cognitive responses, and long-term memory for storing historical interactions. CoPS handles new queries using a three-step approach: identifying re-finding behaviors, constructing user profiles with relevant historical information, and ranking documents based on personalized query intent. Experiments show that CoPS outperforms baseline models in zero-shot scenarios.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Intent-oriented Dynamic Interest Modeling for Personalized Web Search. ACM Transactions on Information Systems 42, 4 (2024), 1–30.
  2. Classification-enhanced ranking. In Proceedings of the WWW’2010. ACM, 111–120.
  3. Modeling the impact of short-and long-term behavior on search personalization. In Proceedings of the SIGIR’2012. ACM, 185–194.
  4. Personalized document re-ranking based on bayesian probabilistic matrix factorization. In Proceedings of the SIGIR’2014. ACM, 835–838.
  5. Towards query log based personalization using topic models. In Proceedings of the CIKM’2010. 1849–1852.
  6. Nelson Cowan. 2008. What are the differences between long-term, short-term, and working memory? Progress in brain research 169 (2008), 323–338.
  7. Uncovering ChatGPT’s Capabilities in Recommender Systems. CoRR abs/2305.02182 (2023).
  8. Convolutional neural networks for soft-matching n-grams in ad-hoc search. In Proceedings of the eleventh ACM international conference on web search and data mining. ACM, 126–134.
  9. Improving Personalized Search with Dual-Feedback Network. In WSDM. ACM, 210–218.
  10. A large-scale evaluation and analysis of personalized search strategies. In WWW’2007, Carey L. Williamson, Mary Ellen Zurko, Peter F. Patel-Schneider, and Prashant J. Shenoy (Eds.). ACM, 581–590.
  11. Recommender Systems in the Era of Large Language Models (LLMs). CoRR abs/2307.02046 (2023).
  12. Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System. CoRR abs/2303.14524 (2023).
  13. Personalizing Search Results Using Hierarchical RNN with Query-aware Attention. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM ’18).
  14. Building user profiles from topic models for personalised search. In CIKM’2013. ACM, 2309–2314.
  15. Large Language Models are Zero-Shot Rankers for Recommender Systems. CoRR abs/2305.08845 (2023).
  16. How Can Recommender Systems Benefit from Large Language Models: A Survey. CoRR abs/2306.05817 (2023).
  17. PSGAN: A Minimax Game for Personalized Search with Limited and Noisy Click Data. In Proceedings of the 42Nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’19).
  18. Helen Neville and Daphne Bavelier. 2002. Human brain plasticity: evidence from sensory deprivation and altered language experience. Progress in brain research 138 (2002), 177–188.
  19. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain, December 9, 2016 (CEUR Workshop Proceedings), Vol. 1773. CEUR-WS.org.
  20. A picture of search.. In InfoScale, Vol. 152. 1.
  21. Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models. CoRR abs/2307.08303 (2023).
  22. Understanding the Behaviors of BERT in Ranking. arXiv preprint arXiv:1904.07531 (2019).
  23. Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting. CoRR abs/2306.17563 (2023).
  24. Stephen E. Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr. 3, 4 (2009), 333–389.
  25. Jennifer K Roth and Susan M Courtney. 2007. Neural system for updating object working memory from different sources: sensory stimuli or long-term memory. Neuroimage 38, 3 (2007), 617–630.
  26. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. ArXiv abs/1910.01108 (2019).
  27. Large Language Models are Strong Zero-Shot Retriever. CoRR abs/2304.14233 (2023).
  28. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent. CoRR abs/2304.09542 (2023).
  29. To personalize or not to personalize: modeling queries with variation in user intent. In SIGIR’2008. ACM, 163–170.
  30. Lei Wang and Ee-Peng Lim. 2023. Zero-Shot Next-Item Recommendation using Large Pretrained Language Models. CoRR abs/2304.03153 (2023).
  31. Incorporating Explicit Subtopics in Personalized Search. In WWW. ACM, 3364–3374.
  32. Enhancing personalized search by mining and modeling task behavior. In WWW’2013. ACM, 1411–1420.
  33. End-to-end neural ad-hoc ranking with kernel pooling. In Proceedings of the 40th International ACM SIGIR conference on research and development in information retrieval. ACM, 55–64.
  34. Employing Personal Word Embeddings for Personalized Search. In SIGIR. ACM, 1359–1368.
  35. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. CoRR abs/2306.05685 (2023).
  36. Group based Personalized Search by Integrating Search Behaviour and Friend Network. In SIGIR. ACM, 92–101.
  37. Encoding History with Context-aware Representation Learning for Personalized Search. In SIGIR. ACM, 1111–1120.
  38. Enhancing Re-finding Behavior with External Memories for Personalized Search. In WSDM. ACM, 789–797.
  39. Enhancing Potential Re-Finding in Personalized Search With Hierarchical Memory Networks. IEEE Trans. Knowl. Data Eng. 35, 4 (2023), 3846–3857.
  40. PSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling. In CIKM. ACM, 2749–2758.
  41. Large Language Models for Information Retrieval: A Survey. CoRR abs/2308.07107 (2023).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Yujia Zhou (34 papers)
  2. Qiannan Zhu (6 papers)
  3. Jiajie Jin (14 papers)
  4. Zhicheng Dou (113 papers)
Citations (11)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now