QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yihang, Huang, Xu, Tian, Bowen, Su, Yueyang, Yu, Lei, Liao, Huaming, Fan, Yixing, Guo, Jiafeng, Cheng, Xueqi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918158858715136
author Wang, Yihang
Huang, Xu
Tian, Bowen
Su, Yueyang
Yu, Lei
Liao, Huaming
Fan, Yixing
Guo, Jiafeng
Cheng, Xueqi
author_facet Wang, Yihang
Huang, Xu
Tian, Bowen
Su, Yueyang
Yu, Lei
Liao, Huaming
Fan, Yixing
Guo, Jiafeng
Cheng, Xueqi
contents Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider adoption, manifested in two main aspects: (i) The excessively long context leads to high costs and inference delays. (ii) A substantial amount of task-irrelevant information introduced by long contexts exacerbates the "lost in the middle" problem. Existing methods compress context by removing redundant tokens using metrics such as self-information or PPL, which is inconsistent with the objective of retaining the most important tokens when conditioning on a given query. In this study, we introduce information bottleneck theory (IB) to model the problem, offering a novel perspective that thoroughly addresses the essential properties required for context compression. Additionally, we propose a cross-attention-based approach to approximate mutual information in IB, which can be flexibly replaced with suitable alternatives in different scenarios. Extensive experiments on four datasets demonstrate that our method achieves a 25% increase in compression rate compared to the state-of-the-art, while maintaining question answering performance. In particular, the context compressed by our method even outperform the full context in some cases.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10497
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
Wang, Yihang
Huang, Xu
Tian, Bowen
Su, Yueyang
Yu, Lei
Liao, Huaming
Fan, Yixing
Guo, Jiafeng
Cheng, Xueqi
Computation and Language
Artificial Intelligence
Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider adoption, manifested in two main aspects: (i) The excessively long context leads to high costs and inference delays. (ii) A substantial amount of task-irrelevant information introduced by long contexts exacerbates the "lost in the middle" problem. Existing methods compress context by removing redundant tokens using metrics such as self-information or PPL, which is inconsistent with the objective of retaining the most important tokens when conditioning on a given query. In this study, we introduce information bottleneck theory (IB) to model the problem, offering a novel perspective that thoroughly addresses the essential properties required for context compression. Additionally, we propose a cross-attention-based approach to approximate mutual information in IB, which can be flexibly replaced with suitable alternatives in different scenarios. Extensive experiments on four datasets demonstrate that our method achieves a 25% increase in compression rate compared to the state-of-the-art, while maintaining question answering performance. In particular, the context compressed by our method even outperform the full context in some cases.
title QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.10497