Sentence-Anchored Gist Compression for Long-Context LLMs

• URL: http://arxiv.org/abs/2511.08128v1
• Date: Wed, 12 Nov 2025 01:41:29 GMT
• Title: Sentence-Anchored Gist Compression for Long-Context LLMs
• Authors: Dmitrii Tarasov, Elizaveta Goncharova, Kuznetsov Andrey,
• Abstract summary: We show that pre-trained Large Language Models can be fine-tuned to compress their context by factors of 2x to 8x without significant performance degradation.<n>Our method achieves results on par with alternative compression techniques while attaining higher compression ratios.
• Score: 3.4406991639518307
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned to compress their context by factors of 2x to 8x without significant performance degradation, as evaluated on both short-context and long-context benchmarks. Furthermore, in experiments on a 3-billion-parameter LLaMA model, our method achieves results on par with alternative compression techniques while attaining higher compression ratios.

Related papers

• Compressing Many-Shots in In-Context Learning [61.231471139896506]
  We study an approach to improve the memory and computational efficiency of ICL inference by compressing the many-shot prompts.<n>We first show that existing prompt compression methods are ineffective for many-shot compression.<n>We propose MemCom, a layer-wise compression method.
  arXiv  Detail & Related papers  (2025-10-17T16:57:42Z)
• Compression Laws for Large Language Models [20.62274005080048]
  We introduce compression laws for language language models (LLMs)<n>We empirically examine the effects of structured model compression on LLMs through over $1000$ experiments.<n>Our findings indicate that the test cross-entropy loss increases quadratically with the compression ratio.
  arXiv  Detail & Related papers  (2025-04-06T03:39:34Z)
• Efficient Long Context Language Model Retrieval with Compression [57.09163579304332]
  Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR)<n>We propose a new compression approach tailored for LCLM retrieval, which is trained to maximize the retrieval performance while minimizing the length of the compressed passages.<n>We show that CoLoR improves the retrieval performance by 6% while compressing the in-context size by a factor of 1.91.
  arXiv  Detail & Related papers  (2024-12-24T07:30:55Z)
• 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)
• LanguaShrink: Reducing Token Overhead with Psycholinguistics [8.123272461141815]
  LanguaShrink is a prompt compression framework for large language models. It reduces prompt length while preserving essential information. Compared to existing prompt compression methods, LanguaShrink improves end-to-end latency by 1.43 times.
  arXiv  Detail & Related papers  (2024-09-01T22:09:20Z)
• In-Context Former: Lightning-fast Compressing Context for Large Language Model [48.831304302467004]
  In this paper, we propose a new approach to compress the long input contexts of Transformer-based large language models (LLMs) We use the cross-attention mechanism and a small number of learnable digest tokens to condense information from the contextual word embeddings. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times.
  arXiv  Detail & Related papers  (2024-06-19T15:14:55Z)
• Evaluating Zero-Shot Long-Context LLM Compression [22.14193187475446]
  This report examines the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context.<n>Due to limited computational resources, our experiments were conducted only on LLaMA-2-7B-32K.
  arXiv  Detail & Related papers  (2024-06-10T20:19:55Z)
• Training LLMs over Neurally Compressed Text [55.11828645767342]
  This paper explores the idea of training large language models (LLMs) over highly compressed text.<n>We propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length.<n>We demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks.
  arXiv  Detail & Related papers  (2024-04-04T17:48:28Z)
• Compressing LLMs: The Truth is Rarely Pure and Never Simple [90.05366363633568]
  Knowledge-Intensive Compressed LLM BenchmarK aims to redefine the evaluation protocol for compressed Large Language Models. LLM-KICK unveils many favorable merits and unfortunate plights of current SoTA compression methods. LLM-KICK is designed to holistically access compressed LLMs' ability for language understanding, reasoning, generation, in-context retrieval, in-context summarization, etc.
  arXiv  Detail & Related papers  (2023-10-02T17:42:37Z)

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.