发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对流式对话摘要场景，提出ReMEMBER缺失证据记忆框架，在固定预算下通过检索未解决窗口依赖的证据并提炼，提升了长历史对话摘要的记忆召回与缺口解决完整性。
AI 中文摘要
现代平台用户频繁需要近期对话的摘要，但当前窗口极少包含足够的上下文以自行解读。我们将此场景形式化为流式对话摘要，即系统必须在固定预算下，利用来自无界历史的选择性记忆，对当前窗口进行摘要。我们表明，核心挑战并非访问多少历史，而是记忆是否恢复了当前窗口预设的证据。我们构建了一个基准和评估协议，分别评估记忆是否包含填补缺口的证据，以及生成的摘要是否反映该证据。我们提出ReMEMBER，一个缺失证据记忆框架，其基于未解决的窗口依赖关系进行检索，并在固定预算下将检索到的片段提炼为证据密集型记忆。对历史长度达160K token的对话进行的实验表明，在相同预算下，ReMEMBER相比记忆构建基线提升了记忆召回率和缺口解决完整性。
英文摘要
Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as streaming dialogue summarization, where a system must summarize a current window using selective memory from an unbounded history under a fixed budget. We show that the central challenge is not how much history is accessed, but whether memory recovers the evidence that the current window presupposes. We construct a benchmark and evaluation protocol that separately assesses whether memory contains gap-resolving evidence and whether the generated summary reflects it. We propose ReMEMBER, a missing-evidence memory framework that conditions retrieval on unresolved window dependencies and refines retrieved chunks into evidence-dense memory under a fixed budget. Experiments on dialogues with histories up to 160K tokens show that ReMEMBER improves memory recall and gap-resolution completeness over memory construction baselines under the same budget.
Comments36 pages, 17 figures, 10 tables
