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

arXiv:2609.31382 · cs.CL, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/X-Luffy/Highlight-Then-Summarize

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Diffusion Process — 6× in this paper · explained in 2 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Grounding — 4× in this paper · explained in 3 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Multi-hop Reasoning — 3× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Entanglement — 1× in this paper · explained in 4 episodes
• Evidence-Summary Quality — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Pruning — 1× in this paper · explained in 4 episodes

Sources

• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
• LongAlign: A Recipe for Long Context Alignment of Large Language Models
• LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
• LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
• Enabling Large Language Models to Generate Text with Citations
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
• GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Kimi K3: Open Frontier Intelligence
• Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
• QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
• LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
• A-MEM: Agentic Memory for LLM Agents
• Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
• HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
• LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering