Lune

ACL Findings2026

BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning

Jia-Chen Gu, Junyi Zhang, Di Wu, Yuankai Li, Kai-Wei Chang, Nanyun Peng

摘要

As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher latency and increased cognitive load on the model. To mitigate this bottleneck, especially for intricate multi-hop questions, we introduce BRIEF-PRO. It is a universal, lightweight compressor that distills relevant evidence for a given query from retrieved documents into a concise summary for seamless integration into in-context RAG. Using seed data consisting of relatively short contexts (fewer than 1k words), BRIEF-PRO is trained to perform abstractive compression of extended contexts exceeding 10k words across a wide range of scenarios. Furthermore, BRIEF-PRO offers flexible user control over summary length by allowing users to specify the desired number of sentences. Experiments on four open-domain multi-hop question-answering datasets show that BRIEF-PRO generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models. With the 70B reader model, 32× compression by BRIEF-PRO improves QA performance by 4.67% on average over LongLLMLingua's 9×, while requiring only 23% of its computational overhead 1 .

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

可以从这些问题问起

Lune 可以查阅

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • Learning to Compress Prompts with Gist Tokens 引用了 LoRA: Low-Rank Adaptation of Large Language Models
  • When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories 引用了 Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

它引用的 Paper18

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni 等NeurIPS 2020 · 19,162 次引用
  2. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 18,833 次引用
  3. Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales 等ICML 2023 · 970 次引用
  4. Learning to Compress Prompts with Gist TokensJesse Mu, Xiang Li, Noah D. GoodmanNeurIPS 2023 · 488 次引用
  5. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric MemoriesAlex Mallen, Akari Asai, Victor Zhong, Rajarshi Das 等ACL 2023 · 233 次引用

相关 Paper

  1. EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented GenerationTaeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song 等ACL Findings 2025 · 10 次引用
  2. CompAct: Compressing Retrieved Documents Actively for Question AnsweringChanwoong Yoon, Taewhoo Lee, Hyeon Hwang, Minbyul Jeong 等EMNLP 2024 · 10 次引用
  3. RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective AugmentationFangyuan Xu, Weijia Shi, Eunsol ChoiICLR 2024 · 260 次引用
  4. Enhancing RAG Efficiency with Adaptive Context CompressionShuyu Guo, Shuo Zhang, Zhaochun RenEMNLP Findings 2025 · 5 次引用
  5. ECoRAG: Evidentiality-guided Compression for Long Context RAGYeonseok Jeong, Jinsu Kim, Dohyeon Lee, Seung-won HwangACL Findings 2025 · 4 次引用
黄昏的海面,两侧是细线勾勒的悬崖