# Finch: Prompt-guided Key-Value Cache Compression

arXiv: https://arxiv.org/abs/2408.00167 · HTML: https://mlsanity.com/paper/2408.00167/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing](https://mlsanity.com/paper/2006.03236/) (2020)

## Built on by (most cited first, 2 of 2)

- [OSCAR: Online Soft Compression And Reranking](https://mlsanity.com/paper/2504.07109/) (2025)
- [Learning What to Remember: Test-Time Training via Context Distillation](https://mlsanity.com/paper/2608.01672/) (2026)

## Abstract (arXiv)

Recent large language model applications, such as Retrieval-Augmented Generation and chatbots, have led to an increased need to process longer input contexts. However, this requirement is hampered by inherent limitations. Architecturally, models are constrained by a context window defined during training. Additionally, processing extensive texts requires substantial GPU memory. We propose a novel approach, Finch, to compress the input context by leveraging the pre-trained model weights of the self-attention. Given a prompt and a long text, Finch iteratively identifies the most relevant Key (K) and Value (V) pairs over chunks of the text conditioned on the prompt. Only such pairs are stored in the KV cache, which, within the space constrained by the context window, ultimately contains a compressed version of the long text. Our proposal enables models to consume large inputs even with high compression (up to 93x) while preserving semantic integrity without the need for fine-tuning.