# From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression

arXiv: https://arxiv.org/abs/2410.04139 · HTML: https://mlsanity.com/paper/2410.04139/

## Key facts

- Cited by 7 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 21 of its 30 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [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)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Learning to Compress Prompt in Natural Language Formats](https://mlsanity.com/paper/2402.18700/) (2024)
- [Discrete Prompt Compression with Reinforcement Learning](https://mlsanity.com/paper/2308.08758/) (2023)
- [Nugget: Neural Agglomerative Embeddings of Text](https://mlsanity.com/paper/2310.01732/) (2023)
- [Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression](https://mlsanity.com/paper/2404.00489/) (2024)

## Built on by (most cited first, 7 of 7)

- [Understanding and Improving Information Preservation in Prompt Compression for LLMs](https://mlsanity.com/paper/2503.19114/) (2025)
- [Draft-based Approximate Inference for LLMs](https://mlsanity.com/paper/2506.08373/) (2025)
- [Conflict-Aware Soft Prompting for Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.15253/) (2025)
- [Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor](https://mlsanity.com/paper/2511.12281/) (2025)
- [IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering](https://mlsanity.com/paper/2608.13588/) (2026)
- [Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors](https://mlsanity.com/paper/2607.25335/) (2026)
- [Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression](https://mlsanity.com/paper/2608.04569/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved significant performance gains using advanced prompting techniques over various tasks. However, the increasing length of prompts leads to high computational costs and often obscures crucial information. Prompt compression has been proposed to alleviate these issues, but it faces challenges in (i) capturing the global context and (ii) training the compressor effectively. To tackle these challenges, we introduce a novel prompt compression method, namely Reading To Compressing (R2C), utilizing the Fusion-in-Decoder (FiD) architecture to identify the important information in the prompt. Specifically, the cross-attention scores of the FiD are used to discern essential chunks and sentences from the prompt. R2C effectively captures the global context without compromising semantic consistency while detouring the necessity of pseudo-labels for training the compressor. Empirical results show that R2C retains key contexts, enhancing the LLM performance by 6% in out-of-domain evaluations while reducing the prompt length by 80%.