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

• URL: http://arxiv.org/abs/2510.13799v1
• Date: Wed, 15 Oct 2025 17:57:45 GMT
• Title: BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
• Authors: Jia-Chen Gu, Junyi Zhang, Di Wu, Yuankai Li, Kai-Wei Chang, Nanyun Peng,
• Abstract summary: BRIEF-Pro is a lightweight compressor that distills relevant evidence for a given query from retrieved documents into a concise summary.<n>It is trained to perform abstractive compression of extended contexts exceeding 10k words across a wide range of scenarios.<n> Experiments show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models.
• Score: 86.4235795435618
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, 32x compression by BRIEF-Pro improves QA performance by 4.67% on average over LongLLMLingua's 9x, while requiring only 23% of its computational overhead.

Related papers

• Stacked from One: Multi-Scale Self-Injection for Context Window Extension [69.24689919827817]
  modelname is a novel framework based on multi-grained context compression and query-aware information acquisition.<n>modelnameachieves performance superior or comparable to strong baselines.
  arXiv  Detail & Related papers  (2026-03-05T03:16:16Z)
• ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG [46.14646374046088]
  ArcAligner is a lightweight module integrated into the language model layers.<n>It uses an adaptive ''gating'' system that only adds extra processing power when the information is complex.
  arXiv  Detail & Related papers  (2026-01-08T15:44:52Z)
• Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning [23.376181947937788]
  We propose task-aware key-value (KV) cache compression, which compresses external knowledge in a zero- or few-shot setup.<n>Experiments show our approach outperforms both RAG and task-agnostic compression methods.<n>A synthetic dataset highlights that RAG performs well when sparse evidence suffices, whereas task-aware compression is superior for broad knowledge tasks.
  arXiv  Detail & Related papers  (2025-03-06T21:07:41Z)
• Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor [16.830389144259584]
  Task-agnostic Prompt Compression (TPC) is a novel framework that generalizes compression across tasks and domains without requiring input questions or templates.<n>TPC generates a context-relevant task description using a task descriptor trained on a curated dataset of context and query pairs.<n>We introduce 3 model sizes (Base, Large, and Huge), where the largest model outperforms the existing state-of-the-art methods on LongBench and ZeroSCROLLS benchmarks.
  arXiv  Detail & Related papers  (2025-02-19T02:16:29Z)
• Efficient Long Context Language Model Retrieval with Compression [57.09163579304332]
  Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR)<n>We propose a new compression approach tailored for LCLM retrieval, which is trained to maximize the retrieval performance while minimizing the length of the compressed passages.<n>We show that CoLoR improves the retrieval performance by 6% while compressing the in-context size by a factor of 1.91.
  arXiv  Detail & Related papers  (2024-12-24T07:30:55Z)
• Two are better than one: Context window extension with multi-grained self-injection [111.1376461868317]
  SharedLLM is a novel approach grounded in the design philosophy of multi-grained context compression and query-aware information retrieval. We introduce a specialized tree-style data structure to efficiently encode, store and retrieve multi-grained contextual information for text chunks.
  arXiv  Detail & Related papers  (2024-10-25T06:08:59Z)
• BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression [91.23933111083389]
  Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge.<n>This paper presents BRIEF, a lightweight approach that performs query-aware multi-hop reasoning.<n>Based on our synthetic data built entirely by open-source models, BRIEF generates more concise summaries.
  arXiv  Detail & Related papers  (2024-10-20T04:24:16Z)
• AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models [15.887617654762629]
  Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. We introduce AdaComp, a low-cost extractive context compression method that adaptively determines the compression rate based on both query complexity and retrieval quality.
  arXiv  Detail & Related papers  (2024-09-03T03:25:59Z)
• ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities [53.97515452727115]
  ChatQA 2 is a Llama 3.0-based model with a 128K context window.<n>We present a training recipe to extend the context window of Llama3-70B-base from 8K to 128K tokens.<n>We find that the performance of strong long-context LLMs using RAG improves when retrieving a larger number of chunks.
  arXiv  Detail & Related papers  (2024-07-19T17:35:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.