生成以探索，选择以利用：将基于LLM的标题生成与个性化推荐对齐
Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation
- Baidu Inc.（百度公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对推荐标题静态呈现难以满足长尾兴趣的问题，提出GESE框架，将个性化解耦为LLM生成候选集与实时选择器利用，显著提升CTR与停留时间。
AI中文摘要：
在工业推荐流中，为物品呈现静态标题往往无法满足用户群体多样化、多模态的兴趣，尤其抑制了长尾受众的需求。尽管大语言模型（LLMs）已被整合到推荐系统中用于内容理解或排序，但直接优化其输出单一最佳标题通常会导致模式坍缩——收敛到迎合平均口味的通用模式，却错失了特定的潜在意图。为弥合这一差距，我们提出了GESE（生成以探索，选择以利用），一个在系统呈现层运作的框架，将个性化解耦为生成性探索与选择性利用。首先，我们将LLM视为概率性探索器，利用带有层次化奖励机制的组序列策略优化（GSPO）生成一个候选集，以最大化潜在用户兴趣的语义覆盖。随后，一个轻量级、实时反馈感知的选择器作为利用器，基于即时上下文信号从候选池中识别出最优实现。在拥有超过1亿日活跃用户的商业平台上的大规模部署表明，GESE显著优于最先进的基线，实现了点击率（CTR）2.57%的提升和停留时间0.87%的提升。这些结果验证了将面向多样性的生成与面向精度的选择解耦，为生成式AI与动态用户效用对齐提供了稳健的蓝图。
英文摘要：
In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user population, particularly suppressing the needs of long-tail audiences. While Large Language Models (LLMs) have been integrated into recommendation for content understanding or ranking, directly optimizing them to output a single best headline typically leads to mode collapse---converging to generic patterns that satisfy average tastes but miss specific latent intents. To bridge this gap, we introduce GESE (Generate to Explore, Select to Exploit), a framework operating at the system's presentation layer that decouples personalization into generative exploration and selective exploitation. First, we treat the LLM as a probabilistic explorer, utilizing Group Sequence Policy Optimization (GSPO) with a hierarchical reward mechanism to generate a candidate set that maximizes the semantic coverage of potential user interests. Subsequently, a lightweight, real-time feedback-aware selector acts as the exploiter, identifying the optimal realization from the candidate pool based on instant contextual signals. Extensive deployment on a commercial platform with over 100 million daily active users demonstrates that GESE significantly outperforms state-of-the-art baselines, achieving a 2.57% lift in CTR and 0.87% in dwell time. These results validate that decoupling diversity-oriented generation from precision-oriented selection offers a robust blueprint for aligning generative AI with dynamic user utility.
