# Long Context In-Context Compression by Getting to the Gist of Gisting

arXiv: https://arxiv.org/abs/2504.08934 · HTML: https://mlsanity.com/paper/2504.08934/

## Key facts

- Cited by 13 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 34 of its 46 references that are in the map.
- First posted on arXiv 11 Apr 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, 30 of 34)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [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)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Towards a Neural Statistician](https://mlsanity.com/paper/1606.02185/) (2016)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [Transformers need glasses! Information over-squashing in language tasks](https://mlsanity.com/paper/2406.04267/) (2024)
- [Softmax is not Enough (for Sharp Size Generalisation)](https://mlsanity.com/paper/2410.01104/) (2024)
- [Compressed Context Memory For Online Language Model Interaction](https://mlsanity.com/paper/2312.03414/) (2023)
- [Discrete Prompt Compression with Reinforcement Learning](https://mlsanity.com/paper/2308.08758/) (2023)
- [PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter](https://mlsanity.com/paper/2310.18347/) (2023)
- [Prompting a Pretrained Transformer Can Be a Universal Approximator](https://mlsanity.com/paper/2402.14753/) (2024)
- [Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs](https://mlsanity.com/paper/2406.02376/) (2024)

## Built on by (most cited first, 13 of 13)

- [COMI: Coarse-to-fine Context Compression via Marginal Information Gain](https://mlsanity.com/paper/2602.01719/) (2026)
- [Read As Human: Compressing Context via Parallelizable Close Reading and Skimming](https://mlsanity.com/paper/2602.01840/) (2026)
- [Simplified Sparse Attention via Gist Tokens](https://mlsanity.com/paper/2604.20920/) (2026)
- [CompLLM: Compression for Long Context Q&A](https://mlsanity.com/paper/2509.19228/) (2025)
- [See, Think, Act: Online Shopper Behavior Simulation with VLM Agents](https://mlsanity.com/paper/2510.19245/) (2025)
- [Compositional Steering of Large Language Models with Steering Tokens](https://mlsanity.com/paper/2601.05062/) (2026)
- [Towards Efficient Agents: A Co-Design of Inference Architecture and System](https://mlsanity.com/paper/2512.18337/) (2025)
- [MARCH: Scaling Recurrent Memory with Content-Routed State Anchors](https://mlsanity.com/paper/2608.12435/) (2026)
- [Cartridges++: KV Cache Compression without Off-Context Derailment](https://mlsanity.com/paper/2609.35621/) (2026)
- [Safin-1: Safety from Within through Memory-Native State Evolution](https://mlsanity.com/paper/2609.00092/) (2026)
- [ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning](https://mlsanity.com/paper/2606.13316/) (2026)
- [Repurposing Pre-trained LLMs as High Fidelity Continuous Text Autoencoders](https://mlsanity.com/paper/2609.27248/) (2026)
- [WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs](https://mlsanity.com/paper/2610.17355/) (2026)

## Abstract (arXiv)

Long context processing is critical for the adoption of LLMs, but existing methods often introduce architectural complexity that hinders their practical adoption. Gisting, an in-context compression method with no architectural modification to the decoder transformer, is a promising approach due to its simplicity and compatibility with existing frameworks. While effective for short instructions, we demonstrate that gisting struggles with longer contexts, with significant performance drops even at minimal compression rates. Surprisingly, a simple average pooling baseline consistently outperforms gisting. We analyze the limitations of gisting, including information flow interruptions, capacity limitations and the inability to restrict its attention to subsets of the context. Motivated by theoretical insights into the performance gap between gisting and average pooling, and supported by extensive experimentation, we propose GistPool, a new in-context compression method. GistPool preserves the simplicity of gisting, while significantly boosting its performance on long context compression tasks.