Image de couverture de livre

Sentence-Anchored Gist Compression for Long-Context LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tarasov, Dmitrii, Goncharova, Elizaveta, Andrey, Kuznetsov
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Image Reconstruction as a Tool for Feature Analysis
par: Allakhverdov, Eduard, et autres
Publié: (2025)

MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing
par: Skripkin, Matvey, et autres
Publié: (2025)

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
par: Li, Pengyi, et autres
Publié: (2026)

Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality
par: Chekalina, Viktoriia, et autres
Publié: (2024)

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
par: Dragunov, Nikita, et autres
Publié: (2025)

Compressing Lengthy Context With UltraGist
par: Zhang, Peitian, et autres
Publié: (2024)

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
par: Razzhigaev, Anton, et autres
Publié: (2025)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
par: Deng, Chenlong, et autres
Publié: (2025)

Simple Vision-Language Math Reasoning via Rendered Text
par: Skripkin, Matvey, et autres
Publié: (2025)

Long Context In-Context Compression by Getting to the Gist of Gisting
par: Petrov, Aleksandar, et autres
Publié: (2025)

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
par: Allakhverdov, Eduard, et autres
Publié: (2025)

Learning to Compress Prompts with Gist Tokens
par: Mu, Jesse, et autres
Publié: (2023)

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
par: Gupta, Shivanshu, et autres
Publié: (2023)

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models
par: Razzhigaev, Anton, et autres
Publié: (2023)

Your Transformer is Secretly Linear
par: Razzhigaev, Anton, et autres
Publié: (2024)

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
par: Lee, Kuang-Huei, et autres
Publié: (2024)

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
par: Deng, Chenlong, et autres
Publié: (2024)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
par: Li, Xinze, et autres
Publié: (2024)

EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
par: Seoh, Ronald, et autres
Publié: (2025)

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs
par: Ghorbanpour, Faeze, et autres
Publié: (2025)

Investigating the Effectiveness of HyperTuning via Gisting
par: Phang, Jason
Publié: (2024)

Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
par: Korzh, Dmitrii, et autres
Publié: (2025)

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
par: Jiang, Huiqiang, et autres
Publié: (2023)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
par: Zhou, Xiabin, et autres
Publié: (2024)

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
par: Peng, Junjie, et autres
Publié: (2026)

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
par: Liskavets, Barys, et autres
Publié: (2024)

Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor
par: Liskavets, Barys, et autres
Publié: (2025)

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
par: Tian, Han, et autres
Publié: (2026)

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
par: Ji, Mengmeng, et autres
Publié: (2026)

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
par: Li, Xuancheng, et autres
Publié: (2026)

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
par: An, Sumin, et autres
Publié: (2025)

Tiny Transformers Excel at Sentence Compression
par: Belcak, Peter, et autres
Publié: (2024)

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
par: Liu, Xin, et autres
Publié: (2025)

Long Context Compression with Activation Beacon
par: Zhang, Peitian, et autres
Publié: (2024)

CompLLM: Compression for Long Context Q&A
par: Berton, Gabriele, et autres
Publié: (2025)

Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking
par: Kokate, Prathamesh, et autres
Publié: (2025)

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
par: Lin, Hongzhan, et autres
Publié: (2024)

UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs
par: Li, Wenhao, et autres
Publié: (2024)

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
par: Wu, Yuhao, et autres
Publié: (2024)

DoubleDipper: Improving Long-Context LLMs via Context Recycling
par: Cattan, Arie, et autres
Publié: (2024)