PACE：挖掘用户请求中的隐藏冲突
PACE: Towards Surfacing Hidden Conflicts in User Requests
浏览论文内容
中文总结 AI 辅助
该研究针对个性化助手的冲突检测需求，构建了数据集 PACE，并提出多智能体框架 PaceMaker，在隐含检索的冲突检测任务上性能优于现有方法。
中文摘要 AI 辅助
个性化助手不仅应遵守用户请求，还需评估这些请求是否符合用户当前的情况。然而，现有工作主要聚焦于准确执行请求，忽略了助手需考虑上下文并基于冲突拒绝的需求。此外，尽管现有的冲突或安全检测工作依赖于明确提供的因素，但现实场景往往涉及必须从知识库（KB）中检索的隐含因素。为此，我们推出了用于冲突评估的个性化助手（PACE），这是一个用于评估模型能否识别潜在约束的数据集，这些约束以自我中心知识或事件的形式表达，会使看似合理的用户请求变得不合适。PACE 将基于明确定义的人设的用户请求与自我中心知识库事实配对，要求模型整合上下文证据以判断请求是否存在冲突。这种隐含检索设置阻碍了用户请求与引发冲突的知识之间的直接关联，导致现有模型难以识别相关的用户特定事实。为应对这一挑战，我们进一步提出了 PaceMaker，这是一个多智能体框架，其中专门的智能体在查询重构、多跳图遍历和冲突感知过滤之间进行协调，以检索具有上下文决定性的证据。在 PACE 上开展的实验同时评估了证据检索质量和冲突决策准确率，结果显示 PaceMaker 的表现始终优于现有方法。
英文摘要
Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately executing requests, overlooking the need for assistants to account for context and engage in conflict-based refusal. Furthermore, while existing work on conflict or safety detection relies on explicitly provided factors, real-world scenarios often involve implicit factors that must be retrieved from a knowledge base (KB). To this end, we introduce Personalized Assistants for Conflict Evaluation (PACE), a dataset for evaluating whether models can identify latent constraints, expressed as egocentric knowledge or events, that render seemingly reasonable user requests inappropriate. PACE pairs user requests grounded in well-defined personas with egocentric KB facts, requiring models to integrate contextual evidence to determine whether a request is conflicting. This implicit retrieval setting hinders the direct association between user requests and conflict-inducing knowledge, making it difficult for existing models to identify relevant user-specific facts. To address this challenge, we further propose PaceMaker, a multi-agent framework in which specialized agents coordinate across query reformulation, multi-hop graph traversal, and conflict-aware filtering to retrieve contextually decisive evidence. Experiments on PACE evaluate both evidence retrieval quality and conflict decision accuracy, showing that PaceMaker consistently outperforms existing approaches.
发表机构
- POSTECH（浦项科技大学）
机构由 AI 辅助整理，请以论文原文为准。
