Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning

• URL: http://arxiv.org/abs/2503.04973v1
• Date: Thu, 06 Mar 2025 21:07:41 GMT
• Title: Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
• Authors: Giulio Corallo, Orion Weller, Fabio Petroni, Paolo Papotti,
• Abstract summary: 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.
• Score: 23.376181947937788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key information may fall outside top ranked results. Long-context models can process multiple documents but are computationally expensive and limited by context window size. Inspired by students condensing study material for open-book exams, we propose task-aware key-value (KV) cache compression, which compresses external knowledge in a zero- or few-shot setup. This enables LLMs to reason efficiently over a compacted representation of all relevant information. Experiments show our approach outperforms both RAG and task-agnostic compression methods. On LongBench v2, it improves accuracy by up to 7 absolute points over RAG with a 30x compression rate, while reducing inference latency from 0.43s to 0.16s. A synthetic dataset highlights that RAG performs well when sparse evidence suffices, whereas task-aware compression is superior for broad knowledge tasks.

Related papers

• Can LLMs Maintain Fundamental Abilities under KV Cache Compression? [29.510433427184385]
  We evaluate KV cache compression methods across diverse tasks, spanning world knowledge, commonsense reasoning, arithmetic reasoning, code generation, safety, and long-context understanding and generation. Our analysis reveals that KV cache compression methods exhibit task-specific performance degradation. We propose ShotKV, a novel compression approach that distinctly handles prefill and decoding phases while maintaining shot-level semantic coherence.
  arXiv  Detail & Related papers  (2025-02-04T02:23:06Z)
• 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)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation [33.13513003367646]
  We propose FaviComp, a training-free evidence compression technique that makes retrieved evidence more familiar to the target model.<n>FaviComp consistently outperforms most recent evidence compression baselines across multiple open-domain QA datasets.
  arXiv  Detail & Related papers  (2024-09-19T05:14:55Z)
• LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression [43.048684907893104]
  This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one. Our approach leads to lower latency by explicitly learning the compression objective with smaller models such as XLM-RoBERTa-large and mBERT.
  arXiv  Detail & Related papers  (2024-03-19T17:59:56Z)
• Long Context Compression with Activation Beacon [22.054232261437186]
  Activation Beacon is a plug-in module for transformer-based LLMs. It targets effective, efficient, and flexible compression of long contexts. It achieves a 2x acceleration in inference time and an 8x reduction of memory costs for KV cache.
  arXiv  Detail & Related papers  (2024-01-07T11:57:40Z)
• RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation [61.53695868960846]
  We propose compressing retrieved documents into textual summaries prior to in-context integration. This not only reduces the computational costs but also relieves the burden of LMs to identify relevant information in long retrieved documents. We show that our compressors trained for one LM can transfer to other LMs on the language modeling task and provide summaries largely faithful to the retrieved documents.
  arXiv  Detail & Related papers  (2023-10-06T17:55:36Z)
• AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models [121.22644352431199]
  We use Neural Architecture Search (NAS) to automatically distill several compressed students with variable cost from a large model. Current works train a single SuperLM consisting of millions ofworks with weight-sharing. Experiments on GLUE benchmark against state-of-the-art KD and NAS methods demonstrate AutoDistil to outperform leading compression techniques.
  arXiv  Detail & Related papers  (2022-01-29T06:13:04Z)
• NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search [100.71365025972258]
  We propose NAS-BERT, an efficient method for BERT compression. NAS-BERT trains a big supernet on a search space and outputs multiple compressed models with adaptive sizes and latency. Experiments on GLUE and SQuAD benchmark datasets demonstrate that NAS-BERT can find lightweight models with better accuracy than previous approaches.
  arXiv  Detail & Related papers  (2021-05-30T07:20:27Z)
• Analyzing and Mitigating JPEG Compression Defects in Deep Learning [69.04777875711646]
  We present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression.
  arXiv  Detail & Related papers  (2020-11-17T20:32:57Z)

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.