Llm maybe longlm: Self-extend llm context window without tuning

H Jin, X Han, J Yang, Z Jiang, Z Liu, CY Chang… - arXiv preprint arXiv …, 2024 - arxiv.org
This work elicits LLMs' inherent ability to handle long contexts without fine-tuning. The
limited length of the training sequence during training may limit the application of Large …

Kv cache compression, but what must we give in return? a comprehensive benchmark of long context capable approaches

J Yuan, H Liu, S Zhong, YN Chuang, S Li… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

CoWPE: Adaptive Context Window Adjustment in LLMs for Complex Input Queries

VM Tamanampudi - … General science (JAIGS) ISSN: 3006-4023, 2024 - ojs.boulibrary.com
Recent work has shown that large language models, or LLMs, are capable of amazing
processing context windows based on the nuance and complexity of respective input …

When Text Embedding Meets Large Language Model: A Comprehensive Survey

Z Nie, Z Feng, M Li, C Zhang, Y Zhang, D Long… - arXiv preprint arXiv …, 2024 - arxiv.org
Text embedding has become a foundational technology in natural language processing
(NLP) during the deep learning era, driving advancements across a wide array of …

From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression

E Choi, S Lee, M Choi, J Park, J Lee - arXiv preprint arXiv:2410.04139, 2024 - arxiv.org
Large language models (LLMs) have achieved significant performance gains using
advanced prompting techniques over various tasks. However, the increasing length of …

TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning

S Shandilya, M Xia, S Ghosh, H Jiang, J Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
The increasing prevalence of large language models (LLMs) such as GPT-4 in various
applications has led to a surge in the size of prompts required for optimal performance …

Enhancing embedding performance through large language model-based text enrichment and rewriting

N Harris, A Butani, S Hashmy - arXiv preprint arXiv:2404.12283, 2024 - arxiv.org
Embedding models are crucial for various natural language processing tasks but can be
limited by factors such as limited vocabulary, lack of context, and grammatical errors. This …

Prompt Compression for Large Language Models: A Survey

Z Li, Y Liu, Y Su, N Collier - arXiv preprint arXiv:2410.12388, 2024 - arxiv.org
Leveraging large language models (LLMs) for complex natural language tasks typically
requires long-form prompts to convey detailed requirements and information, which results …

Lossless KV Cache Compression to 2%

Z Yang, JN Han, K Wu, R Xie, A Wang, X Sun… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models have revolutionized data processing in numerous domains, with
their ability to handle extended context reasoning receiving notable recognition. To speed …

Parse Trees Guided LLM Prompt Compression

W Mao, C Hou, T Zhang, X Lin, K Tang, H Lv - arXiv preprint arXiv …, 2024 - arxiv.org
Offering rich contexts to Large Language Models (LLMs) has shown to boost the
performance in various tasks, but the resulting longer prompt would increase the …