paper-with-me

홈 › Papers

EFPC: Towards Efficient and Flexible Prompt Compression

2025-03-11 · Yun-Hao Cao, Yangsong Wang, Shuzheng Hao, Zhenxing Li, Chengjun Zhan, Sichao Liu, Yi-Qi Hu

The emergence of large language models (LLMs) like GPT-4 has revolutionized natural language processing (NLP), enabling diverse, complex tasks. However, extensive token counts lead to high computational and financial burdens. To address this, we propose Efficient and Flexible Prompt Compression (EFPC), a novel method unifying task-aware and task-agnostic compression for a favorable accuracy-efficiency trade-off. EFPC uses GPT-4 to generate compressed prompts and integrates them with original prompts for training. During training and inference, we selectively prepend user instructions and compress prompts based on predicted probabilities. EFPC is highly data-efficient, achieving significant performance with minimal data. Compared to the state-of-the-art method LLMLingua-2, EFPC achieves a 4.8% relative improvement in F1-score with 1% additional data at a 4x compression rate, and an 11.4% gain with 10% additional data on the LongBench single-doc QA benchmark. EFPC's unified framework supports broad applicability and enhances performance across various models, tasks, and domains, offering a practical advancement in NLP.

📄 PDF Abstract BibTeX arXiv:2503.07956

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

ProCut: LLM Prompt Compression via Attribution Estimation

2025-08-04 · Zhentao Xu, Fengyi Li, Albert Chen, Xiaofeng Wang arxiv

In large-scale industrial LLM systems, prompt templates often expand to thousands of tokens as teams iteratively incorporate sections such as task instructions, few-shot examples, and heuristic rules to enhance robustnes…

VampNet: Music Generation via Masked Acoustic Token Modeling

2023-07-10 · Hugo Flores Garcia, Prem Seetharaman, Rithesh Kumar, Bryan Pardo

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from…

Music CompressionMusic Generation

Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries

2024-12-12 · Junhyuck Kim, Jongho Park, Jaewoong Cho, Dimitris Papailiopoulos

We introduce Lexico, a novel KV cache compression method that leverages sparse coding with a universal dictionary. Our key finding is that key-value cache in modern LLMs can be accurately approximated using sparse linear…

4kGSM8KQuantization

ICPC: In-context Prompt Compression with Faster Inference

2025-01-03 · Ziyang Yu, Yuyu Liu

Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by remov…

Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems

2024-03-30 · Md Adnan Faisal Hossain, Zhihao Duan, Yuning Huang, Fengqing Zhu

Feature compression is a promising direction for coding for machines. Existing methods have made substantial progress, but they require designing and training separate neural network models to meet different specificatio…

Feature Compression