Challenge: Key-Value (KV) caching is widely used in large language models to enable long-context inference efficiently, yet its security implications remain underexplored.
Approach: They propose a history-aware, per-head feedback merging strategy that prevents safety degradation while maintaining efficiency.
Outcome: The proposed strategy prevents safety degradation while maintaining efficiency.

Similar Papers

KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference (2026.eacl-industry)

Copied to clipboard

Challenge: Long-context Large Language Models (LLMs) face significant memory bottlenecks due to the linear growth of key-value (KV) cache with sequence length.
Approach: They propose a framework that maps the trade-off frontier between total memory consumption and task accuracy across three complementary optimization techniques.
Outcome: The proposed model-specific configurations achieve 68-78% total memory reduction with minimal (1-3%) accuracy degradation on long-context tasks.
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are a powerful tool for high-performance inference serving.
Approach: They focus on system-aware KV infrastructure for serving LLMs . they analyze cross-behavior co-design affinity and behavior-objective links .
Outcome: The proposed key-value (KV) cache is crucial for low-latency, high-throughput LLM inference serving.
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.
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 .
ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach: They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome: The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.
A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference (2025.naacl-short)

Copied to clipboard

Challenge: Recent studies have shown that sharing key-value (KV) cache across layers is effective in efficient inference of large language models.
Approach: They propose a unified framework that covers several recent methods and their novel variants to investigate cross-layer KV sharing.
Outcome: The proposed framework achieves higher throughput and better performance when reducing the size of the key-value cache by 2 while maintaining competitive performance.
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to evict keyvalue caches ignore diverse behavior in failure cases, such as bias and distraction.
Approach: They propose a method to analyze attention head behaviors in success and failure scenarios by maximizing signal-to-noise ratio and minimizing noise from bias and distraction.
Outcome: The proposed method achieves comparable accuracy to the strongest baseline, HeadKV-R2 on LongBench v2 while requiring 32x less space.
Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization (2026.acl-long)

Copied to clipboard

Challenge: Recent studies show that KV cache compression can increase hallucination scores in LLMs . modern LLM models support extremely long sequences, but their impact on model hallucinosity remains underexplored.
Approach: They propose a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context.
Outcome: The proposed method reduces hallucination across multiple models and datasets while preserving computational efficiency.
A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to reduce the KV cache size involve fine-tuning the model to learn a compression strategy or leveraging attention scores to reduce sequence length.
Approach: They find a correlation between the L2 norm and attention scores over cached KV pairs . they compress the KV cache based on the L1 norm of key embeddings .
Outcome: The proposed approach reduces the KV cache size by 50% on language modelling and needle-in-a-haystack tasks and 90% on passkey retrieval tasks without losing accuracy.
The Pitfalls of KV Cache Compression (2026.acl-long)

Copied to clipboard

Challenge: Recent literature has shown minimal degradation of KV cache in multi-instruction prompts . authors show that certain instructions degrade much more rapidly with compression .
Approach: They propose to change KV cache eviction policies to reduce the impact of KV evict bias . they propose to use a 'simple' evviction policy to reduce ejection bias if the LLM is a multi-instruction model .
Outcome: The proposed methods show that certain instructions degrade much faster with compression, causing them to be ignored by the LLM.

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