Signals 4 · free daily AI digest

Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding

Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.CL · 自然语言处理 · first seen 2026-09-28

Abstract

Long-context understanding requires large language models (LLMs) to reason over lengthy documents, conversations, and code, yet task-relevant evidence is often sparse and scattered amid substantial irrelevant and redundant content. We propose Highlight-Then-Summarize (H2S), a compress-then-reason paradigm that first identifies source-grounded, question-relevant evidence and then integrates it into

Read on arXiv →

#10 most recent of 267 cs.CL papers we have recorded · ↑ newer: Intent2Tc: Automated Intent-to-Traffic Control Translation with Langua · ↓ older: Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Mo
Cite this page: Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding: the #10 most recent of 267 cs.CL papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/highlight-then-summarize-learning-to-compress-evidence-for-long-context-understa.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions