.</p>\n","updatedAt":"2026-08-11T13:51:25.426Z","author":{"_id":"6510c8ebf26dbb8827ee5e80","avatarUrl":"/avatars/cc49a2f176c951007006e0dae331bc50.svg","fullname":"Hyangsuk Min","name":"hyang0503","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"fr","probability":0.32275810837745667},"editors":["hyang0503"],"editorAvatarUrls":["/avatars/cc49a2f176c951007006e0dae331bc50.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.09043","authors":[{"_id":"6a7b2856b7183653340c128b","user":{"_id":"6510c8ebf26dbb8827ee5e80","avatarUrl":"/avatars/cc49a2f176c951007006e0dae331bc50.svg","isPro":false,"fullname":"Hyangsuk Min","user":"hyang0503","type":"user","name":"hyang0503"},"name":"Hyangsuk Min","status":"claimed_verified","statusLastChangedAt":"2026-08-11T16:45:04.719Z","hidden":false},{"_id":"6a7b2856b7183653340c128c","name":"Hwanjun Song","hidden":false}],"publishedAt":"2026-08-10T00:00:00.000Z","submittedOnDailyAt":"2026-08-11T00:00:00.000Z","title":"Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization","submittedOnDailyBy":{"_id":"6510c8ebf26dbb8827ee5e80","avatarUrl":"/avatars/cc49a2f176c951007006e0dae331bc50.svg","isPro":false,"fullname":"Hyangsuk Min","user":"hyang0503","type":"user","name":"hyang0503"},"summary":"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.","upvotes":1,"discussionId":"6a7b2856b7183653340c128d","ai_summary":"A framework for streaming dialogue summarization retrieves and refines evidence from long histories to resolve missing context in current windows under fixed memory budgets.","ai_keywords":["streaming dialogue summarization","selective memory","gap-resolving evidence","ReMEMBER","missing-evidence memory framework","retrieval conditioning","evidence-dense memory"],"ai_summary_model":"thinkingmachines/Inkling-Small"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.09043.md","query":{}}">
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Abstract
A framework for streaming dialogue summarization retrieves and refines evidence from long histories to resolve missing context in current windows under fixed memory budgets.
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.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.