Resource Consumption Threats in Large Language Models

TL;DR

This paper systematically reviews resource consumption threats in large language models, emphasizing their impact on efficiency, service quality, and economic sustainability, and aims to clarify the problem landscape for mitigation.

Contribution

It provides a comprehensive survey of threats to resource consumption in LLMs, establishing a unified view from threat induction to mitigation strategies.

Findings

Identifies key threats affecting resource efficiency in LLMs

Analyzes the full pipeline from threat induction to mitigation

Clarifies the scope and challenges in resource threat mitigation

Abstract

Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent resource consumption threats induce excessive generation, degrading model efficiency and harming both service availability and economic sustainability. This survey presents a systematic review of threats to resource consumption in LLMs. We further establish a unified view of this emerging area by clarifying its scope and examining the problem along the full pipeline from threat induction to mechanism understanding and mitigation. Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.