Recommendation systems using deep learning are evaluated

The gap

Evidence profile

Sourced from the synthesized and recommendations and future work of the source papers, classified as general, drawn from work published between 2024 and 2026, spanning 3 journals. Those papers have been cited 76 times in total.

Supporting evidence — 4 representative gaps

• The AI-Based Internship Recommendation Engine for PM Internship Scheme (2026) · International Journal of Science, Strategic Management and Technology · doi

  Recommendation systems using deep learning are evaluated on metrics such as accuracy, precision, recall, and user satisfaction, but none of the provided studies examine how users' mental models of the recommendation logic (e.g., explainability, transparency) influence their acceptance and appropriate reliance on AI-generated suggestions.

  generalsynthesized
  Keywords: recommendation systems using deep learning evaluated metrics accuracy
• Scalable multi-metric association rule learning for explainable book recommendations (2026) · Frontiers in Computer Science · doi

  Zhao et al. (2024), the authors presented a thorough survey that delineates significant challenges and opportunities in LLMbased recommendation systems. In Gao et al. (2023), the authors introduced Chat-REC, which demonstrates how conversational interfaces can provide interactive, interpretable recommendations. they proposed LLM4Rec, which treats In Zhu et al. sequential recommendation as language processing and gets the best results so far. In Karlovi et al. (2025), the authors recently developed context-aware LLMs that adapt to users’ contexts, making them more personalized. (2024), 2.5 Explainability and knowledge integration Explainable recommendations are now a major focus, given in developing AI systems that user and regulatory interest are transparent and trustworthy (Zhang et al., 2024). Rule-based recommendation systems have a big advantage over complex deep learning-based recommendation systems, as their logic, which is based on simple if-then rules such as Readers who enjoyed book A also read book B 90% of the time, is immediately understandable without needing any special tool to decode. In (Zhang et al., 2024), the authors demonstrated how providing explanations for such rules in plain language can greatly enhance user trust and system reliability by making the why behind each recommendation crystal clear. In a rule-based approach, you can directly see into the patterns underlying each recommendation, understanding both how the entire system identifies connections across all users and why a particular book is a good recommendation for a given user. This dual transparency arises naturally from the rules. In a neural network-based approach, recommendations are generated through millions of underlying mathematical weights and activations that define a complex embedding of user and item information. To understand why a given book was recommended, researchers must apply a variety of post-hoc analysis tools, such as LIME (Local Interpretable Model-agnostic Explanations), which perturbs inputs to estimate decisions, or SHAP (SHapley Additive exPlanations), which uses game theory to estimate feature contributions. Our ARL method provides the system logic and personalized association rules the explanations it aforementioned techniques used by neural systems. thus bypassing the need for inherently generates, simultaneously through the Knowledge graph-based recommender systems take a different approach by providing direct mappings of relationships among books, such as authors, genres, themes, writing styles, or even publication series. In the case of book recommendations, this could be a historical fiction novel and books by the same author or in the same time period. In Porcel et al. (2012), the authors showed the efficacy of digital libraries using structural relationships, along with the use of sentiment analysis of user book reviews and machine learning, which provided higher user satisfaction levels, as users perceived the recommendations as more in line with their complex tastes rather than popularity-based or co-readingbased recommendations. Multimodal foundation models that combine text, images, and structured data are at the forefront of research (Liu et al., 2024), enabling a deeper understanding of users. In Geng et al. (2022), the authors proposed recommendations for one facet of language processing using new pretraining architectures, while in Wang et al. (2023), they studied generative recommendation as a future direction.

  generalrecommendationsevidence 5/5
  Keywords: based recommendation authors recommendations systems user book users rules explanations language given complex system approach
• Scalable multi-metric association rule learning for explainable book recommendations (2026) · Frontiers in Computer Science · doi

  demand increasingly personalized services, systems will become an indispensable infrastructure. While recent breakthroughs in large language models and deep learning (Nawara and Kashef, 2025; Zhang et al., 2023) open new possibilities, our research demonstrates that traditional data mining techniques like ARL, when properly adapted and executed, remain powerful and explainable approaches for constructing practical recommendation systems that users can understand and trust (Zhang et al., 2024). The proposed framework shows that interpretable ARL-based recommendations can perform competitively while remaining transparent and scalable. In practical applications such as digital libraries, online bookstores, or reading platforms, the system can enhance personalization, reader engagement, and the curation of thematic collections. Future enhancements include expanding long-tail coverage, integrating temporal modeling at the user level, and developing hybrid ARL-neural models that combine explainability with the contextual power of deep learning. The author(s) declared that financial support was not received for this work and/or its publication. Conflict of interest The author(s) declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

  generalrecommendationsevidence 5/5
  Keywords: systems models deep learning zhang practical author declared nancial interest demand increasingly personalized services become
• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2024) · ACM Transactions on Information Systems · cited 76× · doi

  In this paper, we proposed an instruction tuning approach of LLMs for recommender systems, named InstructRec. Different from existing studies that adapt LLMs for recommendation, our key idea is to consider recommendation as instruction following by LLMs, allowing users to freely express their information needs in natural language (called instructions). Specifically, we first designed the general instruction templates format by integrating the preference, intention, and task form, and context information of a user in natural language text. Then, we automatically generated 252K fine-grained user personalized instructions that describe user preferences and intentions. By tuning an open-source LLM (3B Flan-T5-XXL) with these instruction data, the base model can be well adapted to recommender systems, which can follow user’s instructions to perform Zero-shot+Implicit preference+Explicit preference+Specific intention+Vague intention*0.350.450.550.650.75Performance on held-out scenario (HR@1)0.41140.7020.71580.73830.78260.57230.3660HEMGPT-3.5InstructRecRecommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach Conference acronym ’XX, August 03–05, 2022, Woodstock, NY Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023). Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen. 2020. S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization. In CIKM. 1893–1902. Wang-Cheng Kang and Julian McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM. Diane Kelly and Jaime Teevan. 2003. Implicit feedback for inferring user preference: a bibliography. In Acm Sigir Forum, Vol. 37. ACM New York, NY, USA, 18–28. Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009), 30–37. Greg Linden, Brent Smith, and Jeremy York. 2003. Amazon. com recommendations: Item-to-item collaborative filtering. IEEE Internet computing 7, 1 (2003), 76–80. Junling Liu, Chao Liu, Renjie Lv, Kang Zhou, and Yan Zhang. 2023. Is ChatGPT a Good Recommender? A Preliminary Study. arXiv:2304.10149 [cs] Peng Liu, Lemei Zhang, and Jon Atle Gulla. 2023. Pre-train, prompt and recommendation: A comprehensive survey of language modelling paradigm adaptations in recommender systems. arXiv preprint arXiv:2302.03735 (2023). Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730–27744.

  generalfuture workevidence 5/5
  Keywords: language zhang instruction systems recommendation user wang arxiv recommender information instructions llms preference recom zhou

Questions about this gap