paper-with-me

홈 › Papers

Llamazip: Leveraging LLaMA for Lossless Text Compression and Training Dataset Detection

2025-11-16 · Sören Dréano, Derek Molloy, Noel Murphy arxiv

This work introduces Llamazip, a novel lossless text compression algorithm based on the predictive capabilities of the LLaMA3 language model. Llamazip achieves significant data reduction by only storing tokens that the model fails to predict, optimizing storage efficiency without compromising data integrity. Key factors affecting its performance, including quantization and context window size, are analyzed, revealing their impact on compression ratios and computational requirements. Beyond compression, Llamazip demonstrates the potential to identify whether a document was part of the training dataset of a language model. This capability addresses critical concerns about data provenance, intellectual property, and transparency in language model training.

📄 PDF Abstract BibTeX arXiv:2511.17589

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LLMZip: Lossless Text Compression using Large Language Models

2023-06-06 · Chandra Shekhara Kaushik Valmeekam, Krishna Narayanan, Dileep Kalathil, Jean-Francois Chamberland 외

We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smal…

Language ModelingLanguage ModellingLarge Language ModelText Compression

Compression for Better: A General and Stable Lossless Compression Framework

2024-12-09 · Boyang Zhang, Daning Cheng, Yunquan Zhang, Fangmin Liu 외

This work focus on how to stabilize and lossless model compression, aiming to reduce model complexity and enhance efficiency without sacrificing performance due to compression errors. A key challenge is effectively lever…

Computational EfficiencyModel CompressionQuantization

LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression

2026-07-09 · Chris Xing Tian, Chengkai Wu, Ziyu Wang, Rongqun Lin 외 arxiv

Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM proces…

Image Compression

Approximating Human-Like Few-shot Learning with GPT-based Compression

2023-08-14 · Cynthia Huang, Yuqing Xie, Zhiying Jiang, Jimmy Lin 외

In this work, we conceptualize the learning process as information compression. We seek to equip generative pre-trained models with human-like learning capabilities that enable data compression during inference. We prese…

Data CompressionFew-Shot LearningSemantic SimilaritySemantic Textual Similarity+4

ZipNN: Lossless Compression for AI Models

2024-11-07 · Moshik Hershcovitch, Andrew Wood, Leshem Choshen, Guy Girmonsky 외

With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast model compression literatu…

Model Compression