KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches

• URL: http://arxiv.org/abs/2407.01527v2
• Date: Tue, 08 Oct 2024 19:34:03 GMT
• Title: KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
• Authors: Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu,
• Abstract summary: Long context capability is a crucial competency for large language models (LLMs) This work provides a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks.
• Score: 52.02764371205856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-solving scenarios such as book summarization, code assistance, and many more tasks that are traditionally manpower-intensive. However, transformer-based LLMs face significant challenges with long context input due to the growing size of the KV cache and the intrinsic complexity of attending to extended inputs; where multiple schools of efficiency-driven approaches - such as KV cache quantization, token dropping, prompt compression, linear-time sequence models, and hybrid architectures - have been proposed to produce efficient yet long context-capable models. Despite these advancements, no existing work has comprehensively benchmarked these methods in a reasonably aligned environment. In this work, we fill this gap by providing a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks. Our work reveals numerous previously unknown phenomena and offers insights - as well as a friendly workbench - for the future development of long context-capable LLMs. The source code is available at https://github.com/henryzhongsc/longctx_bench.

Related papers

• LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams [4.917265821383127]
  We construct the first spoken long-text dataset, derived from live streams, to reflect the redundancy-rich and conversational nature of real-world scenarios. We evaluate both popular LLMs and specialized methods to assess their ability to understand long-contexts in these tasks. Our findings highlight key limitations of current methods and suggest future directions for improving long-context understanding.
  arXiv  Detail & Related papers  (2025-04-24T08:27:48Z)
• Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation [15.975325252309554]
  We introduce a novel post-training synthetic data generation strategy designed to efficiently extend the context window of Large Language Models. Our approach scalably extends to arbitrarily long context lengths, unconstrained by the length of available real-world data. We demonstrate that our model, with a context length of up to 1M tokens, performs well on the RULER benchmark and InfiniteBench.
  arXiv  Detail & Related papers  (2025-04-17T04:46:57Z)
• LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification [42.54363549922909]
  Speculative decoding has become a promising technique to mitigate the high inference latency of autoregressive decoding in Large Language Models. Despite its promise, the effective application of speculative decoding in LLMs still confronts three key challenges. We enhance the performance of speculative decoding in long-context settings by addressing these challenges.
  arXiv  Detail & Related papers  (2025-02-24T18:53:31Z)
• WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale [86.25450054683172]
  WildLong extracts meta-information from real user queries to produce scalable data. It supports multi-document reasoning, such as cross-document comparison and aggregation. It surpasses existing open-source long-context-optimized models across benchmarks.
  arXiv  Detail & Related papers  (2025-02-23T18:59:09Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective. We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)
• What is Wrong with Perplexity for Long-context Language Modeling? [71.34933096461124]
  Long-context inputs are crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. Perplexity (PPL) has proven unreliable for assessing long-context capabilities. We propose bfLongPPL, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them.
  arXiv  Detail & Related papers  (2024-10-31T09:39:28Z)
• ACER: Automatic Language Model Context Extension via Retrieval [36.40066695682234]
  Current open-weight generalist long-context models are still lacking in practical long-context processing tasks. We build an textbfautomatic data synthesis pipeline that mimics this process using short-context LMs. The short-context LMs are further tuned using these self-generated data to obtain task-specific long-context capabilities.
  arXiv  Detail & Related papers  (2024-10-11T17:57:06Z)
• InfiniPot: Infinite Context Processing on Memory-Constrained LLMs [17.111422610001227]
  InfiniPot is a novel KV cache control framework designed to enable pre-trained Large Language Models to manage extensive sequences efficiently. InfiniPot effectively maintains critical data even without access to future context. This work represents a substantial advancement toward making Large Language Models applicable to a broader range of real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-02T13:09:41Z)
• E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning [20.660297311025417]
  We introduce E2LLM (Encodergated Large Language Models), a novel approach that effectively navigates the "impossible triangle" The method involves splitting long contexts into chunks, compressing each into embedding vectors via a pretrained text encoder, and utilizing an adapter to align these representations with a decoder-only LLM. Experimental results demonstrate that E2LLM achieves superior performance in long-context scenarios while balancing efficiency, performance, and compatibility with pretrained models.
  arXiv  Detail & Related papers  (2024-09-10T17:44:35Z)
• Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption [66.97998742151918]
  Large Language Models (LLMs) have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's struggle with handling long texts. KV Cache has emerged as a pivotal solution, converting the time complexity of token generation from quadratic to linear.
  arXiv  Detail & Related papers  (2024-07-25T12:56:22Z)
• Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning [68.43706033424378]
  This study introduces an innovative method designed to increase in-context text length in large language models (MLLMs) efficiently. We present Visualized In-Context Text Processing (VisInContext), which processes long in-context text using visual tokens. This technique significantly reduces GPU memory usage and floating point operations (FLOPs) for both training and inferenceing stage.
  arXiv  Detail & Related papers  (2024-06-04T17:59:25Z)
• SubGen: Token Generation in Sublinear Time and Memory [48.35076900702408]
  Large language models (LLMs) have extensive memory requirements for token generation. In this work, we focus on developing an efficient compression technique for the KV cache. We have devised a novel caching method with sublinear complexity, employing online clustering on key tokens and online $ell$ sampling on values. Not only does this algorithm ensure a sublinear memory footprint and sublinear time complexity, but we also establish a tight error bound for our approach.
  arXiv  Detail & Related papers  (2024-02-08T22:17:40Z)
• LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding [58.20031627237889]
  LongBench is the first bilingual, multi-task benchmark for long context understanding. It comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese)
  arXiv  Detail & Related papers  (2023-08-28T11:53:40Z)
• KILT: a Benchmark for Knowledge Intensive Language Tasks [102.33046195554886]
  We present a benchmark for knowledge-intensive language tasks (KILT) All tasks in KILT are grounded in the same snapshot of Wikipedia. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline.
  arXiv  Detail & Related papers  (2020-09-04T15:32:19Z)

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.