对话AI数据集|记忆评估数据集

<p>LONGMEMEVAL是由腾讯AI实验室西雅图分部创建的一个综合基准数据集，旨在评估聊天助手在长期交互中的记忆能力。该数据集包含500个高质量问题，覆盖信息提取、跨会话推理、时间推理、知识更新和拒绝回答等五种核心记忆能力。数据集的内容通过多轮任务导向的用户-AI对话生成，历史长度可自由配置，提供了约115k和1.5M tokens的标准设置。创建过程中采用了属性控制的流水线，确保对话历史的连贯性和可扩展性。</p>

LONGMEMEVAL is a comprehensive benchmark dataset developed by the Seattle Branch of Tencent AI Lab, designed to evaluate the memory capabilities of chat assistants during long-term interactions. This dataset contains 500 high-quality questions, covering five core memory capabilities: information extraction, cross-session reasoning, temporal reasoning, knowledge updating, and refusal to answer. The dataset content is generated via multi-turn task-oriented user-AI dialogues, with freely configurable conversation history lengths, and provides standard settings of approximately 115k and 1.5M tokens. A property-controlled pipeline was adopted during the creation process to ensure the coherence and scalability of the conversation histories.