Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chung, Tsz Ting, Cui, Leyang, Liu, Lemao, Huang, Xinting, Shi, Shuming, Yeung, Dit-Yan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917809705975808
author Chung, Tsz Ting
Cui, Leyang
Liu, Lemao
Huang, Xinting
Shi, Shuming
Yeung, Dit-Yan
author_facet Chung, Tsz Ting
Cui, Leyang
Liu, Lemao
Huang, Xinting
Shi, Shuming
Yeung, Dit-Yan
contents Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with in-context learning, several prompt compression methods have been proposed to compress the in-context learning prompts. Despite their success, these methods face challenges with transferability due to model-specific compression, or rely on external training data, such as GPT-4. In this paper, we investigate the ability of LLMs to develop a unified compression method that discretizes uninformative tokens, utilizing a self-supervised pre-training technique. By introducing a small number of parameters during the continual pre-training, the proposed Selection-p produces a probability for each input token, indicating whether to preserve or discard it. Experiments show Selection-p achieves state-of-the-art performance across numerous classification tasks, achieving compression rates of up to 10 times while experiencing only a marginal 0.8% decrease in performance. Moreover, it exhibits superior transferability to different models compared to prior work. Additionally, we further analyze how Selection-p helps maintain performance on in-context learning with long contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11786
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
Chung, Tsz Ting
Cui, Leyang
Liu, Lemao
Huang, Xinting
Shi, Shuming
Yeung, Dit-Yan
Computation and Language
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with in-context learning, several prompt compression methods have been proposed to compress the in-context learning prompts. Despite their success, these methods face challenges with transferability due to model-specific compression, or rely on external training data, such as GPT-4. In this paper, we investigate the ability of LLMs to develop a unified compression method that discretizes uninformative tokens, utilizing a self-supervised pre-training technique. By introducing a small number of parameters during the continual pre-training, the proposed Selection-p produces a probability for each input token, indicating whether to preserve or discard it. Experiments show Selection-p achieves state-of-the-art performance across numerous classification tasks, achieving compression rates of up to 10 times while experiencing only a marginal 0.8% decrease in performance. Moreover, it exhibits superior transferability to different models compared to prior work. Additionally, we further analyze how Selection-p helps maintain performance on in-context learning with long contexts.
title Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.11786