Challenge: Current methods for integrating external knowledge into Large Language Models (LLMs) face limitations with broad, multi-source queries, while long-context models are computationally prohibitive.
Approach: They propose a task-aware key-value cache compression method that generates a sequence of CPTs from a corpus and guides a one-time compression of the corpus into a compact, reusable KV cache.
Outcome: The proposed method outperforms Retrieval-Augmented Generation (RAG) on Question-Answering tasks and reduces latency by over 4.

Similar Papers

MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks.
Approach: They propose a plug-and-play method that uses a key channel's intrinsic quantization difficulty and relevance to the query to identify and preserve critical key channels that need higher precision.
Outcome: Experiments on complex reasoning datasets show that the proposed method outperforms low-bit methods at a substantially reduced memory footprint.
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Copied to clipboard

Challenge: Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach: They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome: The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference (2026.acl-long)

Copied to clipboard

Challenge: Existing static compression methods suffer from coarse-grained caching and high I/O overhead.
Approach: They propose a training-free dynamic compression framework that uses a sparse attention mechanism to categorize attention heads based on stability and similarity.
Outcome: The proposed framework achieves state-of-the-art performance on long-context benchmarks and accelerates decoding by up to 3 compared to the original model with a 224K context.
FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference (2025.findings-emnlp)

Copied to clipboard

Challenge: Key-Value (KV) cache reading latency increases with context lengths hindering LLM inference . important tokens are sparsely distributed across the long context, making existing retrieval inaccurate .
Approach: They propose a method to retain a small fraction of KV cache based on token importance . important tokens are often sparsely distributed across the long context .
Outcome: The proposed method reduces decoding latency by 1.2 to 1.5.
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)

Copied to clipboard

Challenge: Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk.
Approach: They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression.
Outcome: The proposed method surpasses state-of-the-art methods on long context tasks.
CompAct: Compressing Retrieved Documents Actively for Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to condense extensive documents with no loss of information are difficult to implement in real-world scenarios.
Approach: They propose a framework that employs an active strategy to condense extensive documents without losing key information.
Outcome: The proposed framework improves performance and compression rate on multi-hop question-answering benchmarks.
UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Challenge: Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach: They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome: The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics, which hampers the effective retention of essential information while discarding less important tokens.
Approach: They propose a Task-Aware KV cache mechanism that dynamically adjusts the KV caching size across different layers based on the characteristics of the tasks.
Outcome: The proposed method surpasses state-of-the-art methods by 11% on the LongBench dataset even under extreme compression (0.9%)
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) extends large language models with external knowledge, but it must balance limited effective context, redundant retrieved evidence, and the loss of fine-grained facts.
Approach: They propose a hybrid RAG framework that uses natural-language snippets and semantic compression vectors to preserve passages in text form and compress remaining evidence into interpretable vectors for iterative evidence reranking.
Outcome: The proposed framework improves answer relevance, answer correctness and semantic similarity across 9 datasets and 5 open-source LLMs.
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation (2025.acl-long)

Copied to clipboard

Challenge: Excessive compression during the prefill phase impairs comprehension of reasoning tasks . SCOPE is a framework that performs KV cache optimization during the decoding and prefill phases .
Approach: They propose a framework that performs optimization during the prefill and decoding phases . they propose enabling a sliding strategy to select essential heavy hitters for the decoding phase .
Outcome: Experiments show that SCOPE can optimize key-value cache for long-context generation tasks . the framework can preserve essential information while minimizing memory usage and transfer .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations