# Sentence-Anchored Gist Compression for Long-Context LLMs

arXiv: https://arxiv.org/abs/2511.08128 · HTML: https://mlsanity.com/paper/2511.08128/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Prompt and context compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Placed in

- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 18 of 18)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [Long Context Compression with Activation Beacon](https://mlsanity.com/paper/2401.03462/) (2024)
- [Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks](https://mlsanity.com/paper/2407.08454/) (2024)
- [SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator](https://mlsanity.com/paper/2412.12094/) (2024)
- [Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity](https://mlsanity.com/paper/2502.13063/) (2025)
- [A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression](https://mlsanity.com/paper/2412.17483/) (2024)
- [Adaptive Computation Pruning for the Forgetting Transformer](https://mlsanity.com/paper/2504.06949/) (2025)

## Built on by (most cited first, 3 of 3)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent](https://mlsanity.com/paper/2605.24468/) (2026)
- [Compositional Steering of Large Language Models with Steering Tokens](https://mlsanity.com/paper/2601.05062/) (2026)

## Abstract (arXiv)

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned to compress their context by factors of 2x to 8x without significant performance degradation, as evaluated on both short-context and long-context benchmarks. Furthermore, in experiments on a 3-billion-parameter LLaMA model, our method achieves results on par with alternative compression techniques while attaining higher compression ratios.