ES-MemEval：在个性化长期情感支持中评估对话代理的基准测试
ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support
AI总结：
ES-MemEval通过评估长期情感支持中的记忆能力，揭示了显式长期记忆对减少幻觉和提升个性化的重要性，同时指出了检索增强模型在时间动态方面的局限性。
摘要：
大型语言模型（LLMs）在对话代理方面展现出强大的潜力。然而，其有效性仍受到长期记忆鲁棒性的限制，特别是在复杂的长期网络服务中，如在线情感支持。然而，现有的长期对话基准测试主要关注静态和显式的事实检索，未能评估在用户信息分散、隐含且持续变化的场景中代理的表现。为解决这一差距，我们引入了ES-MemEval，一个全面的基准测试，系统评估了长期情感支持场景中的五个核心记忆能力：信息提取、时间推理、冲突检测、回避和用户建模，涵盖问答、总结和对话生成任务。为了支持该基准测试，我们还提出了EvoEmo，一个多会话数据集，用于个性化长期情感支持，捕捉碎片化、隐含的用户披露和变化的用户状态。对开源长上下文、商业和检索增强（RAG）LLMs的大量实验表明，显式的长期记忆对于减少幻觉和实现有效的个性化至关重要。同时，RAG提高了事实一致性，但在时间动态和变化的用户状态方面表现不佳。这些发现突显了当前范式的潜力和局限性，并推动了更稳健的记忆和检索整合，以实现长期个性化对话系统。
英文摘要：
Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities: information extraction, temporal reasoning, conflict detection, abstention, and user modeling, in long-term emotional support settings, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, a multi-session dataset for personalized long-term emotional support that captures fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs show that explicit long-term memory is essential for reducing hallucinations and enabling effective personalization. At the same time, RAG improves factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms and motivate more robust integration of memory and retrieval for long-term personalized dialogue systems.
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。
