# Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression

arXiv: https://arxiv.org/abs/2502.01941 · HTML: https://mlsanity.com/paper/2502.01941/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 70 of its 101 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

## Builds on (most cited first, 30 of 70)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)

## Built on by (most cited first, 16 of 16)

- [Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs](https://mlsanity.com/paper/2512.03324/) (2025)
- [The Pitfalls of KV Cache Compression](https://mlsanity.com/paper/2510.00231/) (2025)
- [FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference](https://mlsanity.com/paper/2505.13109/) (2025)
- [Multipole Attention for Efficient Long Context Reasoning](https://mlsanity.com/paper/2506.13059/) (2025)
- [DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference](https://mlsanity.com/paper/2510.19669/) (2025)
- [SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching](https://mlsanity.com/paper/2504.00970/) (2025)
- [FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management](https://mlsanity.com/paper/2505.15347/) (2025)
- [Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size](https://mlsanity.com/paper/2503.04704/) (2025)
- [AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models](https://mlsanity.com/paper/2506.19505/) (2025)
- [SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching](https://mlsanity.com/paper/2601.21927/) (2026)
- [ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents](https://mlsanity.com/paper/2603.00188/) (2026)
- [NestedKV: Nested Memory Routing for Long-Context KV Cache Compression](https://mlsanity.com/paper/2605.26678/) (2026)
- [Cartridges++: KV Cache Compression without Off-Context Derailment](https://mlsanity.com/paper/2609.35621/) (2026)
- [Reasoning Language Model Inference Serving Unveiled: An Empirical Study](https://mlsanity.com/paper/2510.18672/) (2025)
- [Small Frequency Corrections Can Change What Survives KV Cache Compression](https://mlsanity.com/paper/2608.27128/) (2026)
- [Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2610.05685/) (2026)

## Abstract (arXiv)

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought (CoT) coherence is critical. We introduce KVFundaBench to systematically evaluate this gap, revealing a sharp dichotomy: while retrieval tasks remain robust, reasoning tasks exhibit severe Task-Dependent Degradation under aggressive compression due to disrupted CoT links. Extending our analysis to the DeepSeek-R1 model, we uncover that its specialized attention patterns offer unique insights into the fragility of reasoning chains. Guided by these findings -- specifically the necessity of preserving few-shot examples as indivisible Semantic Units -- we propose ShotKV. This approach explicitly separates prefill and decoding phases to prioritize semantic integrity. Empirical results demonstrate that ShotKV achieves 9%-18% accuracy improvements on long-context generation tasks and effectively generalizes to document QA, all while delivering an 11% latency reduction compared to full cache inference.