发表机构
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS; University of Chinese Academy of Sciences（中国科学院计算技术研究所人工智能安全国家重点实验室; 中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对个性化语言模型固定前置检索记录导致冗余和有害信息的问题，提出ENOUGH方法，通过迭代构建自适应长度的最小充分用户画像，在保持个性化效用的同时降低上下文成本。
AI 中文摘要
检索增强的个性化使得大型语言模型能够利用从用户历史中检索到的相关记录，生成更准确且更符合偏好的输出。个性化语言模型通常会前置固定数量的检索到的用户记录，即使额外的历史信息是冗余的、有害的，或与用户的独特行为无关。我们研究最小充分个性化：为每个输入构建成本最低的有序画像，同时保留从检索到的候选池中可获得的效用。我们提出了ENOUGH方法，该方法迭代地追加行为记录或发出STOP信号，以构建自适应长度的画像。在离线阶段，有界反事实搜索通过联合考虑下游收益、用户特异性和令牌成本来评估画像前缀。由此产生的长时程目标被蒸馏到一个多头价值控制器中，该控制器具有显式的排序和停止监督。在推理时，控制器通过轻量级决策选择和排序记录，并在停止后仅调用一次冻结的生成器。在六个个性化任务上的大量实验表明，ENOUGH在有效性和效率方面均持续优于强启发式基线和检索增强基线，实现了在保留个性化效用的同时减少不必要上下文成本的最小充分画像。
英文摘要
Retrieval-augmented personalization enables large language models to produce more accurate and preference-aligned outputs using relevant records retrieved from user histories. Personalized language models typically prepend a fixed number of retrieved user records, even when additional history is redundant, harmful, or unrelated to a user's distinctive behavior. We study minimal sufficient personalization: constructing the least costly ordered profile for each input while preserving the utility achievable from a retrieved candidate pool. We introduce ENOUGH, a method that iteratively appends behavioral records or emits STOP to construct profiles with adaptive lengths. Offline, bounded counterfactual search evaluates profile prefixes by jointly considering downstream gains, user specificity, and token costs. The resulting long-horizon targets are distilled into a multi-head value controller with explicit ranking and stopping supervision. At inference, the controller selects and orders records through lightweight decisions, and the frozen generator is invoked once after stopping. Extensive experiments on six personalized tasks demonstrate that ENOUGH consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, achieving minimal sufficient profiles that preserve personalization utility while reducing unnecessary context costs.
Comments21 pages
