Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.19235 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915357447421952 |
|---|---|
| author | Xie, Yu Ren, Xingkai Qi, Ying Hu, Yao Shan, Lianlei |
| author_facet | Xie, Yu Ren, Xingkai Qi, Ying Hu, Yao Shan, Lianlei |
| contents | Traditional recommendation systems often grapple with "filter bubbles", underutilization of external knowledge, and a disconnect between model optimization and business policy iteration. To address these limitations, this paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs) and drawing inspiration from the DeepSeek R1 methodology. The framework initiates by transforming user profiles, historical interactions, and multi-faceted item attributes into LLM-interpretable natural language prompts through a carefully engineered data construction process. Subsequently, a two-stage training paradigm is employed: the initial stage involves Supervised Fine-Tuning (SFT) to imbue the LLM with fundamental recommendation capabilities. The subsequent stage utilizes Group Relative Policy Optimization (GRPO), a reinforcement learning technique, augmented with a Chain-of-Thought (CoT) mechanism. This stage guides the model through multi-step reasoning and holistic decision-making via a flexibly defined reward function, aiming to concurrently optimize recommendation accuracy, diversity, and other bespoke business objectives. Empirical evaluations on a real-world user behavior dataset from a large-scale social media platform demonstrate that RecLLM-R1 significantly surpasses existing baseline methods across a spectrum of evaluation metrics, including accuracy, diversity, and novelty. It effectively mitigates the filter bubble effect and presents a promising avenue for the integrated optimization of recommendation models and policies under intricate business goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19235 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Xie, Yu Ren, Xingkai Qi, Ying Hu, Yao Shan, Lianlei Artificial Intelligence Traditional recommendation systems often grapple with "filter bubbles", underutilization of external knowledge, and a disconnect between model optimization and business policy iteration. To address these limitations, this paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs) and drawing inspiration from the DeepSeek R1 methodology. The framework initiates by transforming user profiles, historical interactions, and multi-faceted item attributes into LLM-interpretable natural language prompts through a carefully engineered data construction process. Subsequently, a two-stage training paradigm is employed: the initial stage involves Supervised Fine-Tuning (SFT) to imbue the LLM with fundamental recommendation capabilities. The subsequent stage utilizes Group Relative Policy Optimization (GRPO), a reinforcement learning technique, augmented with a Chain-of-Thought (CoT) mechanism. This stage guides the model through multi-step reasoning and holistic decision-making via a flexibly defined reward function, aiming to concurrently optimize recommendation accuracy, diversity, and other bespoke business objectives. Empirical evaluations on a real-world user behavior dataset from a large-scale social media platform demonstrate that RecLLM-R1 significantly surpasses existing baseline methods across a spectrum of evaluation metrics, including accuracy, diversity, and novelty. It effectively mitigates the filter bubble effect and presents a promising avenue for the integrated optimization of recommendation models and policies under intricate business goals. |
| title | RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.19235 |