Oct 2026· Mathematical Modeling and Algorithm Application· Vol 10, pp. 35-41· 0 citations· 14 references
TL;DR
This paper systematically reviews recent advances in LLM-empowered recommendation systems, and analyzes major challenges related to hallucination, inference efficiency, privacy and security, fairness and trustworthiness, and recommendation agents.
Abstract
Large language models (LLMs) offer new approaches to overcoming the limitations of recommendation systems in representation, user modeling, and decision-making. Accordingly, recommendation systems are evolving from paradigms primarily based on behavioral statistics and discriminative learning toward new paradigms featuring semantic understanding, reasoning-based decision-making, and autonomous interaction. This paper systematically reviews recent advances in LLM-empowered recommendation systems. The principal advantages of LLMs in semantic modeling, knowledge transfer, and generative reasoning are analyzed. Then, the representative technical paradigms including representation-enhanced recommendation, user-interest and context enhancement, prompt learning and task reformulation, and generative recommendation are subsequently reviewed and summarized. Finally, the paper analyzes major challenges related to hallucination, inference efficiency, privacy and security, fairness and trustworthiness, and recommendation agents, and outlines future research directions.
Large language models (LLMs) bring world knowledge to user preference modeling in sequential recommendation, but generation-based recommenders express next-item predictions indirectly as text. Generated outputs may fail to identify a unique candidate item, depend on candidate presentation order in the prompt, and lack...
Dao-Xuan Liu, Jia-Yi Liao, Jian-Can Wu et al.· 0 citations
A series of models are explored that connect item Semantic IDs with natural language in a unified representation space and seek to unlock the potential of natural-language chain-of-thought (CoT) reasoning for recommendation, including OneReason.
Recommender systems are ubiquitous on the Web, making understandable explanations essential for users. Although large language models (LLMs) increasingly generate natural-language justifications, evaluating their factual grounding and personalized relevance remains challenging. Statement-level ranking offers an alterna...
Despite the adoption of large language models (LLMs) in recommendation systems, prevailing approaches mostly model single-type behaviors (e.g., views or purchases). Even when incorporating multiple behaviors, existing methods flatten heterogeneous actions into homogeneous token sequences, ignoring their distinct decisi...
Lei Liang, Guo-Shuai Wang, Xin He et al.· 0 citations
Generative recommendation promises to simplify conventional multi-stage recommender systems by generating item Semantic IDs (SIDs) autoregressively. However, two obstacles limit its effective- ness in industrial settings: interaction-only supervision underuses the semantic knowledge encoded in pretrained language model...
Zhuo-Hang Jiang, Yu-Xin Chen, Hao-Hao Qu et al.· 0 citations
This work formalise recommendation as a Partially Observable Markov Decision Process and proposes a unified, three-tier agentic framework that couples a simulation environment (RecoWorld), a reproducible policy engine (RecBole), and a cognitive LLM user agent.
Ionuț-Dragoș Neremzoiu, C. Bǎdicǎ· Electronics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.