SafeCRS: 为基于大语言模型的对话推荐系统实现个性化安全对齐
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
AI总结：
SafeCRS通过整合安全监督微调与安全组奖励解耦归一化策略优化，提升基于大语言模型的对话推荐系统在个性化安全约束下的推荐质量与安全对齐能力。
摘要：
当前基于大语言模型的对话推荐系统（CRS）主要优化推荐准确性和用户满意度。我们发现了一个未被充分探索的漏洞，即推荐输出可能通过违反个性化安全约束而对用户产生负面影响，当个体化的安全敏感性（如创伤触发、自残史或恐惧症）从对话中隐式推断但未在推荐过程中得到尊重时。我们正式将这一挑战定义为个性化CRS安全，并引入SafeRec，一个新设计的基准数据集，旨在系统评估基于大语言模型的CRS在用户特定约束下的安全风险。为进一步解决这一问题，我们提出了SafeCRS，一种安全意识训练框架，它将Safe Supervised Fine-Tuning（Safe-SFT）与Safe Group reward-Decoupled Normalization Policy Optimization（Safe-GDPO）相结合，以联合优化推荐质量与个性化安全对齐。在SafeRec上的大量实验表明，SafeCRS在保持竞争力的推荐质量的同时，将安全违规率降低了高达96.5%，相对于最强的推荐质量基线。警告：本文可能包含潜在有害和冒犯性内容。
英文摘要：
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which recommendation outputs may negatively impact users by violating personalized safety constraints, when individualized safety sensitivities -- such as trauma triggers, self-harm history, or phobias -- are implicitly inferred from the conversation but not respected during recommendation. We formalize this challenge as personalized CRS safety and introduce SafeRec, a new benchmark dataset designed to systematically evaluate safety risks in LLM-based CRS under user-specific constraints. To further address this problem, we propose SafeCRS, a safety-aware training framework that integrates Safe Supervised Fine-Tuning (Safe-SFT) with Safe Group reward-Decoupled Normalization Policy Optimization (Safe-GDPO) to jointly optimize recommendation quality and personalized safety alignment. Extensive experiments on SafeRec demonstrate that SafeCRS reduces safety violation rates by up to 96.5% relative to the strongest recommendation-quality baseline while maintaining competitive recommendation quality. Warning: This paper contains potentially harmful and offensive content.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
