PACE：面向用户请求中潜在冲突的揭示

摘要

个性化助手不仅应当遵从用户的请求，还应当评估这些请求在用户当前情境下是否恰当。然而，以往的工作主要聚焦于准确执行请求，忽视了助手需要考虑情境并进行基于冲突的拒绝。此外，现有的冲突或安全检测工作依赖于显式提供的因素，而现实场景往往涉及必须从知识库（KB）中检索的隐式因素。为此，我们提出了用于冲突评估的个性化助手数据集（PACE），用于评估模型能否识别使看似合理的用户请求变得不恰当的潜在约束（以自我中心知识或事件的形式表达）。PACE 将基于明确人设的用户请求与自我中心知识库事实配对，要求模型整合情境证据以判断请求是否存在冲突。这种隐式检索设置阻碍了用户请求与冲突诱发知识之间的直接关联，使得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，一种多智能体框架，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协同配合，以检索具有情境决定性的证据。在 PACE 上的实验既评估了证据检索质量，也评估了冲突决策准确性，结果表明 PaceMaker 始终优于现有方法。

English

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.