When Relevance Meets Novelty: Dual-Stable Periodic Optimization for Exploratory Recommendation
This work addresses content fatigue and limited exploration in recommendation systems for users, representing an incremental improvement over existing LLM-enhanced frameworks.
The paper tackles the problem of recommendation systems trapping users in feedback loops by proposing the Co-Evolutionary Alignment (CoEA) method, which addresses biases in interest modeling and static optimization limitations, resulting in verified effectiveness in exploratory recommendation through online and offline experiments.
Traditional recommendation systems tend to trap users in strong feedback loops by excessively pushing content aligned with their historical preferences, thereby limiting exploration opportunities and causing content fatigue. Although large language models (LLMs) demonstrate potential with their diverse content generation capabilities, existing LLM-enhanced dual-model frameworks face two major limitations: first, they overlook long-term preferences driven by group identity, leading to biased interest modeling; second, they suffer from static optimization flaws, as a one-time alignment process fails to leverage incremental user data for closed-loop optimization. To address these challenges, we propose the Co-Evolutionary Alignment (CoEA) method. For interest modeling bias, we introduce Dual-Stable Interest Exploration (DSIE) module, jointly modeling long-term group identity and short-term individual interests through parallel processing of behavioral sequences. For static optimization limitations, we design a Periodic Collaborative Optimization (PCO) mechanism. This mechanism regularly conducts preference verification on incremental data using the Relevance LLM, then guides the Novelty LLM to perform fine-tuning based on the verification results, and subsequently feeds back the output of the incrementally fine-tuned Novelty LLM to the Relevance LLM for re-evaluation, thereby achieving a dynamic closed-loop optimization. Extensive online and offline experiments verify the effectiveness of the CoEA model in exploratory recommendation.