Copertina

Sentence-Anchored Gist Compression for Long-Context LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tarasov, Dmitrii, Goncharova, Elizaveta, Andrey, Kuznetsov
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Image Reconstruction as a Tool for Feature Analysis
di: Allakhverdov, Eduard, et al.
Pubblicazione: (2025)

MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing
di: Skripkin, Matvey, et al.
Pubblicazione: (2025)

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
di: Li, Pengyi, et al.
Pubblicazione: (2026)

Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality
di: Chekalina, Viktoriia, et al.
Pubblicazione: (2024)

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
di: Dragunov, Nikita, et al.
Pubblicazione: (2025)

Compressing Lengthy Context With UltraGist
di: Zhang, Peitian, et al.
Pubblicazione: (2024)

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
di: Razzhigaev, Anton, et al.
Pubblicazione: (2025)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
di: Deng, Chenlong, et al.
Pubblicazione: (2025)

Simple Vision-Language Math Reasoning via Rendered Text
di: Skripkin, Matvey, et al.
Pubblicazione: (2025)

Long Context In-Context Compression by Getting to the Gist of Gisting
di: Petrov, Aleksandar, et al.
Pubblicazione: (2025)

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
di: Allakhverdov, Eduard, et al.
Pubblicazione: (2025)

Learning to Compress Prompts with Gist Tokens
di: Mu, Jesse, et al.
Pubblicazione: (2023)

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
di: Gupta, Shivanshu, et al.
Pubblicazione: (2023)

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models
di: Razzhigaev, Anton, et al.
Pubblicazione: (2023)

Your Transformer is Secretly Linear
di: Razzhigaev, Anton, et al.
Pubblicazione: (2024)

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
di: Lee, Kuang-Huei, et al.
Pubblicazione: (2024)

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
di: Deng, Chenlong, et al.
Pubblicazione: (2024)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
di: Li, Xinze, et al.
Pubblicazione: (2024)

EmoGist: Efficient In-Context Learning for Visual Emotion Understanding
di: Seoh, Ronald, et al.
Pubblicazione: (2025)

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs
di: Ghorbanpour, Faeze, et al.
Pubblicazione: (2025)

Investigating the Effectiveness of HyperTuning via Gisting
di: Phang, Jason
Pubblicazione: (2024)

Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
di: Korzh, Dmitrii, et al.
Pubblicazione: (2025)

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
di: Jiang, Huiqiang, et al.
Pubblicazione: (2023)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
di: Zhou, Xiabin, et al.
Pubblicazione: (2024)

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
di: Peng, Junjie, et al.
Pubblicazione: (2026)

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
di: Liskavets, Barys, et al.
Pubblicazione: (2024)

Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor
di: Liskavets, Barys, et al.
Pubblicazione: (2025)

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
di: Tian, Han, et al.
Pubblicazione: (2026)

LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning
di: Ji, Mengmeng, et al.
Pubblicazione: (2026)

ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs
di: Li, Xuancheng, et al.
Pubblicazione: (2026)

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
di: An, Sumin, et al.
Pubblicazione: (2025)

Tiny Transformers Excel at Sentence Compression
di: Belcak, Peter, et al.
Pubblicazione: (2024)

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
di: Liu, Xin, et al.
Pubblicazione: (2025)

Long Context Compression with Activation Beacon
di: Zhang, Peitian, et al.
Pubblicazione: (2024)

CompLLM: Compression for Long Context Q&A
di: Berton, Gabriele, et al.
Pubblicazione: (2025)

Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking
di: Kokate, Prathamesh, et al.
Pubblicazione: (2025)

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
di: Lin, Hongzhan, et al.
Pubblicazione: (2024)

UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs
di: Li, Wenhao, et al.
Pubblicazione: (2024)

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
di: Wu, Yuhao, et al.
Pubblicazione: (2024)

DoubleDipper: Improving Long-Context LLMs via Context Recycling
di: Cattan, Arie, et al.
Pubblicazione: (2024)