# LLMs for User Interest Exploration in Large-scale Recommendation Systems

arXiv: https://arxiv.org/abs/2405.16363 · HTML: https://mlsanity.com/paper/2405.16363/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 25 May 2024.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Text Is All You Need: Learning Language Representations for Sequential Recommendation](https://mlsanity.com/paper/2305.13731/) (2023)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders](https://mlsanity.com/paper/2210.12316/) (2022)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [VIP5: Towards Multimodal Foundation Models for Recommendation](https://mlsanity.com/paper/2305.14302/) (2023)
- [Large Language Models for User Interest Journeys](https://mlsanity.com/paper/2305.15498/) (2023)
- [Large Language Models as Data Augmenters for Cold-Start Item Recommendation](https://mlsanity.com/paper/2402.11724/) (2024)
- [Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation](https://mlsanity.com/paper/2112.00944/) (2021)
- [TagGPT: Large Language Models are Zero-shot Multimodal Taggers](https://mlsanity.com/paper/2304.03022/) (2023)
- [Long-Term Value of Exploration: Measurements, Findings and Algorithms](https://mlsanity.com/paper/2305.07764/) (2023)
- [Result Diversification in Search and Recommendation: A Survey](https://mlsanity.com/paper/2212.14464/) (2022)
- [Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations](https://mlsanity.com/paper/2110.09905/) (2021)

## Built on by (most cited first, 15 of 15)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [RecoWorld: Building Simulated Environments for Agentic Recommender Systems](https://mlsanity.com/paper/2509.10397/) (2025)
- [Improving LLM-powered Recommendations with Personalized Information](https://mlsanity.com/paper/2502.13845/) (2025)
- [Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge](https://mlsanity.com/paper/2508.08777/) (2025)
- [Graph Foundation Models for Recommendation: A Comprehensive Survey](https://mlsanity.com/paper/2502.08346/) (2025)
- [RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference](https://mlsanity.com/paper/2601.01712/) (2026)
- [IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data](https://mlsanity.com/paper/2506.02449/) (2025)
- [When Relevance Meets Novelty: Dual-Stable Periodic Optimization for Serendipitous Recommendation](https://mlsanity.com/paper/2508.00450/) (2025)
- [CoNRec: Context-Discerning Negative Recommendation with LLMs](https://mlsanity.com/paper/2601.15721/) (2026)
- [Bridging Textual Profiles and Latent User Embeddings for Personalization](https://mlsanity.com/paper/2605.06981/) (2026)
- [Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning](https://mlsanity.com/paper/2605.15299/) (2026)
- [ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling](https://mlsanity.com/paper/2606.24605/) (2026)
- [NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model](https://mlsanity.com/paper/2607.24789/) (2026)
- [PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks](https://mlsanity.com/paper/2608.21381/) (2026)

## Abstract (arXiv)

Traditional recommendation systems are subject to a strong feedback loop by learning from and reinforcing past user-item interactions, which in turn limits the discovery of novel user interests. To address this, we introduce a hybrid hierarchical framework combining Large Language Models (LLMs) and classic recommendation models for user interest exploration. The framework controls the interfacing between the LLMs and the classic recommendation models through "interest clusters", the granularity of which can be explicitly determined by algorithm designers. It recommends the next novel interests by first representing "interest clusters" using language, and employs a fine-tuned LLM to generate novel interest descriptions that are strictly within these predefined clusters. At the low level, it grounds these generated interests to an item-level policy by restricting classic recommendation models, in this case a transformer-based sequence recommender to return items that fall within the novel clusters generated at the high level. We showcase the efficacy of this approach on an industrial-scale commercial platform serving billions of users. Live experiments show a significant increase in both exploration of novel interests and overall user enjoyment of the platform.